import pandas as pan
import numpy as np
import plotly.express as px
pays = "en Suisse romande"
media1 = pan.read_csv("suisse-motsSeuls-media-nettoye.csv", low_memory=False, names=["mot","interactions"])
nonmedia1 = pan.read_csv("suisse-motsSeuls-nonmedia-nettoye.csv", low_memory=False, names=["mot","interactions"])
media1
| mot | interactions | |
|---|---|---|
| 0 | donner | 49596 |
| 1 | enfant | 49596 |
| 2 | envie | 49596 |
| 3 | intéresser | 49596 |
| 4 | biodiversité | 49596 |
| ... | ... | ... |
| 4393344 | formulaire | 0 |
| 4393345 | ici | 0 |
| 4393346 | jardinière | 0 |
| 4393347 | recruter | 0 |
| 4393348 | rtn | 0 |
4393349 rows × 2 columns
nonmedia1
| mot | interactions | |
|---|---|---|
| 0 | falloir | 107933 |
| 1 | il | 107933 |
| 2 | faire | 107933 |
| 3 | petit | 107933 |
| 4 | prince | 107933 |
| ... | ... | ... |
| 8890675 | dal | 0 |
| 8890676 | tuo | 0 |
| 8890677 | background | 0 |
| 8890678 | maggiori | 0 |
| 8890679 | informazioni | 0 |
8890680 rows × 2 columns
media1_table = pan.pivot_table(media1,index=["mot"],values=["mot","interactions"],aggfunc=[len,np.sum])
nonmedia1_table = pan.pivot_table(nonmedia1,index=["mot"],values=["mot","interactions"],aggfunc=[len,np.sum])
media1_table
| len | sum | |
|---|---|---|
| interactions | interactions | |
| mot | ||
| #12h45rts | 2 | 200 |
| #19h30rt | 2 | 15 |
| #coronaviru | 1 | 325 |
| #couleurslocales | 2 | 111 |
| #covid19 | 13 | 2360 |
| ... | ... | ... |
| 수원 | 1 | 8 |
| 시즌 | 1 | 8 |
| 이동국 | 1 | 8 |
| 이동국의 | 1 | 8 |
| 전북 | 1 | 8 |
95205 rows × 2 columns
nonmedia1_table
| len | sum | |
|---|---|---|
| interactions | interactions | |
| mot | ||
| #111 | 1 | 5 |
| #6 | 1 | 1 |
| #7 | 1 | 36 |
| #allezlausanne | 1 | 105 |
| #allezxamax | 4 | 257 |
| ... | ... | ... |
| samedi | 1 | 43 |
| sea | 3 | 30 |
| sen | 1 | 0 |
| sonore | 1 | 0 |
| spontanes | 2 | 0 |
217662 rows × 2 columns
media1_table["type"] = "media"
nonmedia1_table["type"] = "non-media"
media1_table
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| mot | |||
| #12h45rts | 2 | 200 | media |
| #19h30rt | 2 | 15 | media |
| #coronaviru | 1 | 325 | media |
| #couleurslocales | 2 | 111 | media |
| #covid19 | 13 | 2360 | media |
| ... | ... | ... | ... |
| 수원 | 1 | 8 | media |
| 시즌 | 1 | 8 | media |
| 이동국 | 1 | 8 | media |
| 이동국의 | 1 | 8 | media |
| 전북 | 1 | 8 | media |
95205 rows × 3 columns
nonmedia1_table
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| mot | |||
| #111 | 1 | 5 | non-media |
| #6 | 1 | 1 | non-media |
| #7 | 1 | 36 | non-media |
| #allezlausanne | 1 | 105 | non-media |
| #allezxamax | 4 | 257 | non-media |
| ... | ... | ... | ... |
| samedi | 1 | 43 | non-media |
| sea | 3 | 30 | non-media |
| sen | 1 | 0 | non-media |
| sonore | 1 | 0 | non-media |
| spontanes | 2 | 0 | non-media |
217662 rows × 3 columns
tableau1 = pan.concat([media1_table,nonmedia1_table], names = ["mot","nb","interactions","type"], levels=0)
tableau1
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| mot | |||
| #12h45rts | 2 | 200 | media |
| #19h30rt | 2 | 15 | media |
| #coronaviru | 1 | 325 | media |
| #couleurslocales | 2 | 111 | media |
| #covid19 | 13 | 2360 | media |
| ... | ... | ... | ... |
| samedi | 1 | 43 | non-media |
| sea | 3 | 30 | non-media |
| sen | 1 | 0 | non-media |
| sonore | 1 | 0 | non-media |
| spontanes | 2 | 0 | non-media |
312867 rows × 3 columns
tableau1["mot"] = tableau1.index
tableau1.columns = ["nb","interactions","media","mot"]
tableau1.reset_index(drop=True, inplace=True)
tableau1
| nb | interactions | media | mot | |
|---|---|---|---|---|
| 0 | 2 | 200 | media | #12h45rts |
| 1 | 2 | 15 | media | #19h30rt |
| 2 | 1 | 325 | media | #coronaviru |
| 3 | 2 | 111 | media | #couleurslocales |
| 4 | 13 | 2360 | media | #covid19 |
| ... | ... | ... | ... | ... |
| 312862 | 1 | 43 | non-media | samedi |
| 312863 | 3 | 30 | non-media | sea |
| 312864 | 1 | 0 | non-media | sen |
| 312865 | 1 | 0 | non-media | sonore |
| 312866 | 2 | 0 | non-media | spontanes |
312867 rows × 4 columns
khi2_1 = pan.pivot_table(tableau1,index=["mot"],columns=["media"],values=["mot","interactions"],aggfunc=[len,np.sum],fill_value=0)
khi2_1
| len | sum | |||||||
|---|---|---|---|---|---|---|---|---|
| interactions | nb | interactions | nb | |||||
| media | media | non-media | media | non-media | media | non-media | media | non-media |
| mot | ||||||||
| #111 | 0 | 1 | 0 | 1 | 0 | 5 | 0 | 1 |
| #12h45rts | 1 | 0 | 1 | 0 | 200 | 0 | 2 | 0 |
| #19h30rt | 1 | 0 | 1 | 0 | 15 | 0 | 2 | 0 |
| #6 | 0 | 1 | 0 | 1 | 0 | 1 | 0 | 1 |
| #7 | 0 | 1 | 0 | 1 | 0 | 36 | 0 | 1 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... |
| samedi | 0 | 1 | 0 | 1 | 0 | 43 | 0 | 1 |
| sea | 0 | 1 | 0 | 1 | 0 | 30 | 0 | 3 |
| sen | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 1 |
| sonore | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 1 |
| spontanes | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 2 |
251466 rows × 8 columns
khi2_1["mot"] = khi2_1.index
khi2_1.columns = khi2_1.columns.get_level_values(0)
khi2_1.reset_index(drop=True, inplace=True)
khi2_1.columns = ["a","b","c","d","interactions_media","interactions_nonmedia","obs_media","obs_nonmedia","mot"]
khi2_1 = khi2_1.drop(columns=["a","b","c","d"])
khi2_1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | |
|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 |
| 1 | 200 | 0 | 2 | 0 | #12h45rts |
| 2 | 15 | 0 | 2 | 0 | #19h30rt |
| 3 | 0 | 1 | 0 | 1 | #6 |
| 4 | 0 | 36 | 0 | 1 | #7 |
| ... | ... | ... | ... | ... | ... |
| 251461 | 0 | 43 | 0 | 1 | samedi |
| 251462 | 0 | 30 | 0 | 3 | sea |
| 251463 | 0 | 0 | 0 | 1 | sen |
| 251464 | 0 | 0 | 0 | 1 | sonore |
| 251465 | 0 | 0 | 0 | 2 | spontanes |
251466 rows × 5 columns
khi2_1.obs_media.sum(), khi2_1.obs_nonmedia.sum()
(4393348, 8890588)
print("Nb de lignes fichier media1 = ", media1.shape[0])
print("Somme observée média khi2_1 = ", khi2_1.obs_media.sum())
print("Nb de lignes fichier nonmedia1 = ", nonmedia1.shape[0])
print("Somme observée nonmédia khi2_1 = ", khi2_1.obs_nonmedia.sum())
Nb de lignes fichier media1 = 4393349 Somme observée média khi2_1 = 4393348 Nb de lignes fichier nonmedia1 = 8890680 Somme observée nonmédia khi2_1 = 8890588
khi2_1["exp_media"] = ((khi2_1.obs_media + khi2_1.obs_nonmedia) * khi2_1.obs_media.sum()) / (khi2_1.obs_media.sum() + khi2_1.obs_nonmedia.sum())
khi2_1["exp_nonmedia"] = ((khi2_1.obs_media + khi2_1.obs_nonmedia) * khi2_1.obs_nonmedia.sum()) / (khi2_1.obs_media.sum() + khi2_1.obs_nonmedia.sum())
khi2_1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | |
|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 | 0.330726 | 0.669274 |
| 1 | 200 | 0 | 2 | 0 | #12h45rts | 0.661453 | 1.338547 |
| 2 | 15 | 0 | 2 | 0 | #19h30rt | 0.661453 | 1.338547 |
| 3 | 0 | 1 | 0 | 1 | #6 | 0.330726 | 0.669274 |
| 4 | 0 | 36 | 0 | 1 | #7 | 0.330726 | 0.669274 |
| ... | ... | ... | ... | ... | ... | ... | ... |
| 251461 | 0 | 43 | 0 | 1 | samedi | 0.330726 | 0.669274 |
| 251462 | 0 | 30 | 0 | 3 | sea | 0.992179 | 2.007821 |
| 251463 | 0 | 0 | 0 | 1 | sen | 0.330726 | 0.669274 |
| 251464 | 0 | 0 | 0 | 1 | sonore | 0.330726 | 0.669274 |
| 251465 | 0 | 0 | 0 | 2 | spontanes | 0.661453 | 1.338547 |
251466 rows × 7 columns
khi2_1["res_media"] = (khi2_1.obs_media - khi2_1.exp_media) / np.sqrt(khi2_1.exp_media)
khi2_1["res_nonmedia"] = (khi2_1.obs_nonmedia - khi2_1.exp_nonmedia) / np.sqrt(khi2_1.exp_nonmedia)
khi2_1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 | 0.330726 | 0.669274 | -0.575088 | 0.404266 |
| 1 | 200 | 0 | 2 | 0 | #12h45rts | 0.661453 | 1.338547 | 1.645827 | -1.156956 |
| 2 | 15 | 0 | 2 | 0 | #19h30rt | 0.661453 | 1.338547 | 1.645827 | -1.156956 |
| 3 | 0 | 1 | 0 | 1 | #6 | 0.330726 | 0.669274 | -0.575088 | 0.404266 |
| 4 | 0 | 36 | 0 | 1 | #7 | 0.330726 | 0.669274 | -0.575088 | 0.404266 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 251461 | 0 | 43 | 0 | 1 | samedi | 0.330726 | 0.669274 | -0.575088 | 0.404266 |
| 251462 | 0 | 30 | 0 | 3 | sea | 0.992179 | 2.007821 | -0.996082 | 0.700209 |
| 251463 | 0 | 0 | 0 | 1 | sen | 0.330726 | 0.669274 | -0.575088 | 0.404266 |
| 251464 | 0 | 0 | 0 | 1 | sonore | 0.330726 | 0.669274 | -0.575088 | 0.404266 |
| 251465 | 0 | 0 | 0 | 2 | spontanes | 0.661453 | 1.338547 | -0.813297 | 0.571718 |
251466 rows × 9 columns
graph_media1 = khi2_1.sort_values(by=["res_media"],ascending=False).head(50)
graph_media1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 63253 | 4149267 | 2064994 | 31611 | 23430 | coronavirus | 18203.510410 | 36837.489590 | 99.373342 | -69.855798 |
| 214837 | 4796589 | 4058911 | 42891 | 37794 | suisse | 26684.657573 | 54000.342427 | 99.209713 | -69.740773 |
| 49667 | 1406213 | 769170 | 12838 | 7239 | canton | 6639.993432 | 13437.006568 | 76.062082 | -53.468841 |
| 97318 | 122000 | 97710 | 5358 | 1188 | football | 2164.934851 | 4381.065149 | 68.625475 | -48.241180 |
| 100618 | 1393898 | 611575 | 10073 | 7190 | fédéral | 5709.329413 | 11553.670587 | 57.750987 | -40.596815 |
| 231498 | 437696 | 350223 | 4106 | 1105 | valaisan | 1723.415141 | 3487.584859 | 57.392273 | -40.344653 |
| 135419 | 94100 | 115024 | 4472 | 1425 | league | 1950.293434 | 3946.706566 | 57.101113 | -40.139978 |
| 170201 | 976427 | 639521 | 8918 | 5954 | pandémie | 4918.562650 | 9953.437350 | 57.026904 | -40.087812 |
| 98401 | 448226 | 184717 | 5528 | 2578 | franc | 2680.867996 | 5425.132004 | 54.988249 | -38.654713 |
| 232384 | 424106 | 292245 | 5545 | 2759 | vaudois | 2746.351819 | 5557.648181 | 53.403561 | -37.540736 |
| 64476 | 2208219 | 1380470 | 14422 | 13895 | covid-19 | 9365.178763 | 18951.821237 | 52.254003 | -36.732639 |
| 113513 | 133183 | 157688 | 4124 | 1686 | hockey | 1921.520239 | 3888.479761 | 50.244606 | -35.320107 |
| 141459 | 844279 | 403020 | 7886 | 5850 | lundi | 4542.857488 | 9193.142512 | 49.600989 | -34.867667 |
| 50752 | 1560407 | 1034103 | 8529 | 6639 | cas | 5016.457657 | 10151.542343 | 49.593298 | -34.862261 |
| 248746 | 308359 | 166994 | 3828 | 1499 | évolution | 1761.779400 | 3565.220600 | 49.226723 | -34.604572 |
| 40536 | 91758 | 46109 | 2713 | 643 | bienne | 1109.917715 | 2246.082285 | 48.118316 | -33.825403 |
| 126744 | 169070 | 70334 | 3063 | 968 | jurassien | 1333.158018 | 2697.841982 | 47.376789 | -33.304137 |
| 160297 | 616425 | 592349 | 8933 | 7563 | neuchâtel | 5455.662283 | 11040.337717 | 47.078556 | -33.094490 |
| 192518 | 244069 | 88470 | 2058 | 242 | restezchezvous | 760.670663 | 1539.329337 | 47.038331 | -33.066214 |
| 160311 | 278821 | 197860 | 4389 | 2255 | neuchâtelois | 2197.346036 | 4446.653964 | 46.754429 | -32.866641 |
| 23798 | 44137 | 33569 | 2411 | 503 | alpha | 963.736657 | 1950.263343 | 46.619582 | -32.771848 |
| 126703 | 243753 | 168092 | 3621 | 1530 | jura | 1703.571558 | 3447.428442 | 46.455696 | -32.656643 |
| 39244 | 124746 | 62927 | 2385 | 505 | bernois | 955.799224 | 1934.200776 | 46.228511 | -32.496940 |
| 138268 | 52101 | 59326 | 2857 | 926 | ligue | 1251.137877 | 2531.862123 | 45.399981 | -31.914514 |
| 145302 | 647636 | 300044 | 6717 | 5172 | mardi | 3932.005873 | 7956.994127 | 44.413726 | -31.221212 |
| 92024 | 708603 | 954021 | 8726 | 7781 | face | 5459.300273 | 11047.699727 | 44.212057 | -31.079447 |
| 149179 | 694881 | 361135 | 7159 | 5780 | mercredi | 4279.268567 | 8659.731433 | 44.021741 | -30.945662 |
| 39207 | 287615 | 290843 | 3313 | 1455 | berne | 1576.903356 | 3191.096644 | 43.719115 | -30.732927 |
| 78918 | 530653 | 143424 | 2836 | 1057 | décès | 1287.517778 | 2605.482222 | 43.154849 | -30.336269 |
| 154392 | 119643 | 19100 | 2009 | 399 | morges | 796.389111 | 1611.610889 | 42.969352 | -30.205871 |
| 103351 | 1614616 | 1121151 | 13056 | 14228 | genève | 9023.538418 | 18260.461582 | 42.450402 | -29.841068 |
| 59637 | 244884 | 172102 | 4686 | 3016 | commune | 2547.254541 | 5154.745459 | 42.376290 | -29.788970 |
| 93595 | 149483 | 397870 | 5219 | 3633 | fc | 2927.589872 | 5924.410128 | 42.349444 | -29.770098 |
| 73441 | 719051 | 772325 | 7999 | 7157 | dimanche | 5012.488941 | 10143.511059 | 42.182995 | -29.653091 |
| 103175 | 561834 | 184280 | 5068 | 3488 | genevois | 2829.694865 | 5726.305135 | 42.077457 | -29.578902 |
| 183502 | 564133 | 369689 | 6482 | 5235 | président | 3875.120937 | 7841.879063 | 41.877260 | -29.438170 |
| 226850 | 314163 | 218315 | 3423 | 1740 | trump | 1707.540275 | 3455.459725 | 41.514045 | -29.182844 |
| 125789 | 110511 | 287173 | 3729 | 2062 | joueur | 1915.236438 | 3875.763562 | 41.444745 | -29.134129 |
| 151035 | 490438 | 797249 | 6534 | 5369 | million | 3936.636043 | 7966.363957 | 41.397125 | -29.100653 |
| 27861 | 177332 | 33345 | 2121 | 590 | app | 896.599203 | 1814.400797 | 40.890689 | -28.744648 |
| 89018 | 207327 | 32124 | 2525 | 967 | etats-unis | 1154.896502 | 2337.103498 | 40.316409 | -28.340950 |
| 53102 | 58556 | 105197 | 2880 | 1305 | championnat | 1384.089880 | 2800.910120 | 40.209008 | -28.265451 |
| 185693 | 425287 | 141646 | 3005 | 1450 | quarantaine | 1473.386001 | 2981.613999 | 39.901669 | -28.049403 |
| 195021 | 473294 | 243486 | 4932 | 3638 | romand | 2834.325034 | 5735.674966 | 39.401556 | -27.697842 |
| 61339 | 1434466 | 925400 | 13613 | 15817 | conseil | 9733.277218 | 19696.722782 | 39.325219 | -27.644180 |
| 111511 | 106582 | 131096 | 2933 | 1423 | hc | 1440.644090 | 2915.355910 | 39.318239 | -27.639273 |
| 220495 | 54529 | 26329 | 1650 | 330 | tennis | 654.838223 | 1325.161777 | 38.888991 | -27.337528 |
| 26233 | 879275 | 614067 | 7538 | 7094 | annoncer | 4839.188320 | 9792.811680 | 38.795944 | -27.272119 |
| 54033 | 209656 | 135217 | 3543 | 2131 | chaux-de-fonds | 1876.541452 | 3797.458548 | 38.469402 | -27.042572 |
| 232888 | 743931 | 464749 | 7777 | 7502 | vendredi | 5053.168285 | 10225.831715 | 38.317608 | -26.935867 |
fig = px.bar(graph_media1, x="res_media", y="mot", labels={"res_media":"Résiduel de Pearson","mot":"Lemme (dans les posts Facebook <b>médias</b>)"}, orientation="h", title="Lemmes les plus caractéristiques des posts Facebook <b>médias</b> {} en 2020".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="red", opacity=0.75, textfont_size=12)
fig
graph_nonmedia1 = khi2_1.sort_values(by=["res_nonmedia"],ascending=False).head(50)
graph_nonmedia1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 174900 | 299280 | 7716498 | 3976 | 55597 | photo | 19702.362342 | 39870.637658 | -112.038975 | 78.759271 |
| 78831 | 409877 | 2873301 | 5611 | 46373 | découvrir | 17192.479882 | 34791.520118 | -88.327267 | 62.090814 |
| 114262 | 1757 | 30933 | 339 | 24059 | horoscope | 8069.062099 | 16328.937901 | -86.054078 | 60.492846 |
| 222630 | 15728 | 4913467 | 428 | 20718 | timeline | 6993.539927 | 14152.460073 | -78.509447 | 55.189248 |
| 206547 | 59933 | 221399 | 1264 | 22084 | signe | 7721.799405 | 15626.200595 | -73.489500 | 51.660411 |
| 7200 | 465833 | 1856324 | 9397 | 43319 | 2020 | 17434.571588 | 35281.428412 | -60.872230 | 42.790935 |
| 120529 | 57503 | 291927 | 708 | 13905 | 4832.904519 | 9780.095481 | -59.334842 | 41.710208 | |
| 24895 | 51410 | 1508070 | 708 | 13768 | amour | 4787.595006 | 9688.404994 | -58.960119 | 41.446791 |
| 134072 | 31334 | 16163 | 37 | 8855 | lanta | 2940.818927 | 5951.181073 | -53.547030 | 37.641589 |
| 130232 | 31562 | 16208 | 39 | 8795 | koh | 2921.636797 | 5912.363203 | -53.330642 | 37.489476 |
| 92731 | 31997 | 192328 | 797 | 11779 | fan | 4159.214893 | 8416.785107 | -52.133849 | 36.648175 |
| 64050 | 131934 | 315661 | 943 | 12228 | couple | 4355.997086 | 8815.002914 | -51.712094 | 36.351697 |
| 99564 | 70893 | 2086825 | 1191 | 12900 | from | 4660.265351 | 9430.734649 | -50.819712 | 35.724385 |
| 189082 | 47510 | 288848 | 1139 | 12649 | recette | 4560.055260 | 9227.944740 | -50.661149 | 35.612921 |
| 221318 | 90292 | 714511 | 1196 | 12449 | the | 4512.761388 | 9132.238612 | -49.373401 | 34.707682 |
| 201406 | 266828 | 2108996 | 3333 | 19568 | savoir | 7573.964716 | 15327.035284 | -48.730742 | 34.255916 |
| 179062 | 195944 | 2173828 | 1893 | 14551 | post | 5438.464512 | 11005.535488 | -48.076738 | 33.796175 |
| 94082 | 652920 | 1531120 | 4957 | 23640 | femme | 9457.782148 | 19139.217852 | -46.279999 | 32.533134 |
| 248831 | 292681 | 2070334 | 3042 | 17399 | être | 6760.377833 | 13680.622167 | -45.223902 | 31.790737 |
| 125994 | 168005 | 1082434 | 2821 | 16467 | journée | 6379.050322 | 12908.949678 | -44.548601 | 31.316025 |
| 95268 | 292091 | 708656 | 997 | 10108 | fille | 3672.716395 | 7432.283605 | -44.151594 | 31.036943 |
| 53810 | 151589 | 665568 | 522 | 8104 | chat | 2852.845711 | 5773.154289 | -43.638959 | 30.676580 |
| 92355 | 1115645 | 4240036 | 11721 | 40260 | faire | 17191.487703 | 34789.512297 | -41.722403 | 29.329312 |
| 54778 | 202932 | 760769 | 1037 | 9342 | chien | 3432.609047 | 6946.390953 | -40.888744 | 28.743281 |
| 54634 | 13262 | 277547 | 653 | 7886 | chf | 2824.072517 | 5714.927483 | -40.854171 | 28.718977 |
| 237433 | 193748 | 1629315 | 2696 | 14725 | vous | 5761.584180 | 11659.415820 | -40.387065 | 28.390618 |
| 110243 | 5544 | 704174 | 37 | 4854 | hallyday | 1617.582700 | 3273.417300 | -39.299224 | 27.625907 |
| 32433 | 0 | 7505 | 0 | 4457 | auproux | 1474.047454 | 2982.952546 | -38.393326 | 26.989093 |
| 38238 | 148809 | 1942899 | 1969 | 11751 | bel | 4537.565866 | 9182.434134 | -38.131091 | 26.804752 |
| 20882 | 7473 | 8241 | 37 | 4522 | agathe | 1507.781544 | 3051.218456 | -37.877295 | 26.626343 |
| 24911 | 36456 | 468685 | 401 | 6126 | amoureux | 2158.651050 | 4368.348950 | -37.830444 | 26.593408 |
| 11018 | 1469 | 768904 | 77 | 4473 | 3 | 1504.805007 | 3045.194993 | -36.806861 | 25.873867 |
| 31057 | 4 | 11896 | 2 | 4067 | astrologique | 1345.725620 | 2723.274380 | -36.629614 | 25.749269 |
| 92112 | 21440 | 270797 | 509 | 6213 | facile | 2223.142693 | 4498.857307 | -36.354929 | 25.556176 |
| 25381 | 13880 | 274397 | 287 | 5114 | and | 1786.253152 | 3614.746848 | -35.473453 | 24.936530 |
| 186609 | 23196 | 100911 | 133 | 4417 | race | 1504.805007 | 3045.194993 | -35.363258 | 24.859067 |
| 231222 | 195676 | 491076 | 1886 | 10685 | vacance | 4157.561261 | 8413.438739 | -35.229390 | 24.764963 |
| 50756 | 15381 | 17863 | 41 | 3874 | casa | 1294.793758 | 2620.206242 | -34.843823 | 24.493924 |
| 170452 | 2513 | 14743 | 28 | 3795 | papel | 1264.366932 | 2558.633068 | -34.770490 | 24.442374 |
| 107089 | 83816 | 317902 | 999 | 7580 | gratuit | 2837.301572 | 5741.698428 | -34.511514 | 24.260322 |
| 245439 | 137 | 21480 | 12 | 3651 | zodiaque | 1211.450712 | 2451.549288 | -34.461131 | 24.224906 |
| 165418 | 153631 | 511024 | 1103 | 7919 | of | 2983.813356 | 6038.186644 | -34.431812 | 24.204295 |
| 183342 | 14226 | 275465 | 173 | 4394 | prénom | 1510.427355 | 3056.572645 | -34.412821 | 24.190945 |
| 223150 | 48583 | 274699 | 248 | 4331 | to | 1514.396071 | 3064.603929 | -32.542418 | 22.876121 |
| 197947 | 67202 | 159920 | 657 | 5902 | réserve | 2169.234294 | 4389.765706 | -32.468771 | 22.824350 |
| 148453 | 163390 | 1051836 | 2541 | 11814 | meilleur | 4747.577114 | 9607.422886 | -32.024554 | 22.512082 |
| 171247 | 98476 | 904647 | 1388 | 8253 | partager | 3188.532982 | 6452.467018 | -31.886410 | 22.414971 |
| 177642 | 25458 | 91485 | 409 | 4843 | poids | 1736.974922 | 3515.025078 | -31.863472 | 22.398847 |
| 234818 | 797121 | 3693372 | 5483 | 19793 | vie | 8359.439856 | 16916.560144 | -31.460579 | 22.115628 |
| 2380 | 319608 | 1135228 | 3082 | 13221 | 10 | 5391.832093 | 10911.167907 | -31.456633 | 22.112854 |
fig = px.bar(graph_nonmedia1, x="res_nonmedia", y="mot", labels={"res_nonmedia":"Résiduel de Pearson","mot":"Lemme (dans les posts Facebook <b>non-médias</b>)"}, orientation="h", title="Lemmes les plus caractéristiques des posts Facebook <b>non-médias</b> {} en 2020".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="darkorange", opacity=0.75, textfont_size=12)
fig
khi2_1["exp_inter_media"] = ((khi2_1.interactions_media + khi2_1.interactions_nonmedia) * khi2_1.interactions_media.sum()) / (khi2_1.interactions_media.sum() + khi2_1.interactions_nonmedia.sum())
khi2_1["exp_inter_nonmedia"] = ((khi2_1.interactions_media + khi2_1.interactions_nonmedia) * khi2_1.interactions_nonmedia.sum()) / (khi2_1.interactions_media.sum() + khi2_1.interactions_nonmedia.sum())
khi2_1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 1.334422 | 3.665578 |
| 1 | 200 | 0 | 2 | 0 | #12h45rts | 0.661453 | 1.338547 | 1.645827 | -1.156956 | 53.376886 | 146.623114 |
| 2 | 15 | 0 | 2 | 0 | #19h30rt | 0.661453 | 1.338547 | 1.645827 | -1.156956 | 4.003266 | 10.996734 |
| 3 | 0 | 1 | 0 | 1 | #6 | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 0.266884 | 0.733116 |
| 4 | 0 | 36 | 0 | 1 | #7 | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 9.607839 | 26.392161 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 251461 | 0 | 43 | 0 | 1 | samedi | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 11.476030 | 31.523970 |
| 251462 | 0 | 30 | 0 | 3 | sea | 0.992179 | 2.007821 | -0.996082 | 0.700209 | 8.006533 | 21.993467 |
| 251463 | 0 | 0 | 0 | 1 | sen | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 0.000000 | 0.000000 |
| 251464 | 0 | 0 | 0 | 1 | sonore | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 0.000000 | 0.000000 |
| 251465 | 0 | 0 | 0 | 2 | spontanes | 0.661453 | 1.338547 | -0.813297 | 0.571718 | 0.000000 | 0.000000 |
251466 rows × 11 columns
khi2_1["res_inter_media"] = (khi2_1.interactions_media - khi2_1.exp_inter_media) / np.sqrt(khi2_1.exp_inter_media)
khi2_1["res_inter_nonmedia"] = (khi2_1.interactions_nonmedia - khi2_1.exp_inter_nonmedia) / np.sqrt(khi2_1.exp_inter_nonmedia)
khi2_1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 1.334422 | 3.665578 | -1.155172 | 0.696983 |
| 1 | 200 | 0 | 2 | 0 | #12h45rts | 0.661453 | 1.338547 | 1.645827 | -1.156956 | 53.376886 | 146.623114 | 20.069004 | -12.108803 |
| 2 | 15 | 0 | 2 | 0 | #19h30rt | 0.661453 | 1.338547 | 1.645827 | -1.156956 | 4.003266 | 10.996734 | 5.496123 | -3.316132 |
| 3 | 0 | 1 | 0 | 1 | #6 | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 0.266884 | 0.733116 | -0.516609 | 0.311700 |
| 4 | 0 | 36 | 0 | 1 | #7 | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 9.607839 | 26.392161 | -3.099652 | 1.870201 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 251461 | 0 | 43 | 0 | 1 | samedi | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 11.476030 | 31.523970 | -3.387629 | 2.043955 |
| 251462 | 0 | 30 | 0 | 3 | sea | 0.992179 | 2.007821 | -0.996082 | 0.700209 | 8.006533 | 21.993467 | -2.829582 | 1.707252 |
| 251463 | 0 | 0 | 0 | 1 | sen | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 0.000000 | 0.000000 | NaN | NaN |
| 251464 | 0 | 0 | 0 | 1 | sonore | 0.330726 | 0.669274 | -0.575088 | 0.404266 | 0.000000 | 0.000000 | NaN | NaN |
| 251465 | 0 | 0 | 0 | 2 | spontanes | 0.661453 | 1.338547 | -0.813297 | 0.571718 | 0.000000 | 0.000000 | NaN | NaN |
251466 rows × 13 columns
graph_interactions_media1 = khi2_1.sort_values(by=["res_inter_media"],ascending=False).head(50)
graph_interactions_media1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 63253 | 4149267 | 2064994 | 31611 | 23430 | coronavirus | 18203.510410 | 36837.489590 | 99.373342 | -69.855798 | 1.658489e+06 | 4.555772e+06 | 1934.098426 | -1166.954619 |
| 214837 | 4796589 | 4058911 | 42891 | 37794 | suisse | 26684.657573 | 54000.342427 | 99.209713 | -69.740773 | 2.363395e+06 | 6.492105e+06 | 1582.736305 | -954.957317 |
| 64476 | 2208219 | 1380470 | 14422 | 13895 | covid-19 | 9365.178763 | 18951.821237 | 52.254003 | -36.732639 | 9.577652e+05 | 2.630924e+06 | 1277.727129 | -770.927454 |
| 100618 | 1393898 | 611575 | 10073 | 7190 | fédéral | 5709.329413 | 11553.670587 | 57.750987 | -40.596815 | 5.352295e+05 | 1.470243e+06 | 1173.695651 | -708.159183 |
| 49667 | 1406213 | 769170 | 12838 | 7239 | canton | 6639.993432 | 13437.006568 | 76.062082 | -53.468841 | 5.805758e+05 | 1.594807e+06 | 1083.576913 | -653.785281 |
| 50752 | 1560407 | 1034103 | 8529 | 6639 | cas | 5016.457657 | 10151.542343 | 49.593298 | -34.862261 | 6.924343e+05 | 1.902076e+06 | 1043.077947 | -629.349888 |
| 103351 | 1614616 | 1121151 | 13056 | 14228 | genève | 9023.538418 | 18260.461582 | 42.450402 | -29.841068 | 7.301336e+05 | 2.005633e+06 | 1035.113607 | -624.544537 |
| 61339 | 1434466 | 925400 | 13613 | 15817 | conseil | 9733.277218 | 19696.722782 | 39.325219 | -27.644180 | 6.298115e+05 | 1.730055e+06 | 1013.921099 | -611.757858 |
| 191715 | 572057 | 103322 | 2368 | 1080 | reportage | 1140.344541 | 2307.655459 | 36.354523 | -25.555890 | 1.802481e+05 | 4.951309e+05 | 922.866454 | -556.819269 |
| 141459 | 844279 | 403020 | 7886 | 5850 | lundi | 4542.857488 | 9193.142512 | 49.600989 | -34.867667 | 3.328847e+05 | 9.144143e+05 | 886.357643 | -534.791370 |
| 149526 | 1310710 | 1091592 | 8975 | 9332 | mesure | 6054.607748 | 12252.392252 | 37.531695 | -26.383399 | 6.411370e+05 | 1.761165e+06 | 836.223783 | -504.542682 |
| 170201 | 976427 | 639521 | 8918 | 5954 | pandémie | 4918.562650 | 9953.437350 | 57.026904 | -40.087812 | 4.312714e+05 | 1.184677e+06 | 830.128265 | -500.864900 |
| 116002 | 930148 | 582889 | 4595 | 3870 | hôpital | 2799.598765 | 5665.401235 | 33.932325 | -23.853174 | 4.038060e+05 | 1.109231e+06 | 828.288480 | -499.754850 |
| 78918 | 530653 | 143424 | 2836 | 1057 | décès | 1287.517778 | 2605.482222 | 43.154849 | -30.336269 | 1.799007e+05 | 4.941763e+05 | 826.959443 | -498.952964 |
| 146403 | 1015564 | 695958 | 4926 | 5810 | masque | 3550.678363 | 7185.321637 | 23.080680 | -16.224868 | 4.567786e+05 | 1.254743e+06 | 826.784282 | -498.847279 |
| 103175 | 561834 | 184280 | 5068 | 3488 | genevois | 2829.694865 | 5726.305135 | 42.077457 | -29.578902 | 1.991262e+05 | 5.469878e+05 | 812.816801 | -490.419882 |
| 231492 | 918817 | 612192 | 6099 | 5261 | valais | 3757.051621 | 7602.948379 | 38.207950 | -26.858781 | 4.086025e+05 | 1.122407e+06 | 798.182752 | -481.590304 |
| 145302 | 647636 | 300044 | 6717 | 5172 | mardi | 3932.005873 | 7956.994127 | 44.413726 | -31.221212 | 2.529210e+05 | 6.947590e+05 | 784.858048 | -473.550732 |
| 149179 | 694881 | 361135 | 7159 | 5780 | mercredi | 4279.268567 | 8659.731433 | 44.021741 | -30.945662 | 2.818342e+05 | 7.741818e+05 | 778.040790 | -469.437482 |
| 12040 | 306092 | 7468 | 85 | 61 | 369 | 48.286051 | 97.713949 | 5.283482 | -3.714093 | 8.368428e+04 | 2.298757e+05 | 768.825730 | -463.877497 |
| 26233 | 879275 | 614067 | 7538 | 7094 | annoncer | 4839.188320 | 9792.811680 | 38.795944 | -27.272119 | 3.985497e+05 | 1.094792e+06 | 761.475083 | -459.442422 |
| 163130 | 1877064 | 2214889 | 17062 | 27093 | nouveau | 14603.223091 | 29551.776909 | 20.346737 | -14.303006 | 1.092079e+06 | 2.999874e+06 | 751.163845 | -453.221050 |
| 232888 | 743931 | 464749 | 7777 | 7502 | vendredi | 5053.168285 | 10225.831715 | 38.317608 | -26.935867 | 3.225779e+05 | 8.861021e+05 | 741.871926 | -447.614692 |
| 185693 | 425287 | 141646 | 3005 | 1450 | quarantaine | 1473.386001 | 2981.613999 | 39.901669 | -28.049403 | 1.513056e+05 | 4.156274e+05 | 704.358257 | -424.980503 |
| 200079 | 810826 | 612714 | 8141 | 8666 | samedi | 5558.518186 | 11248.481814 | 34.638395 | -24.349515 | 3.799207e+05 | 1.043619e+06 | 699.093752 | -421.804119 |
| 196090 | 399170 | 129226 | 2453 | 2352 | rts | 1589.140232 | 3215.859768 | 21.670161 | -15.233325 | 1.410207e+05 | 3.873753e+05 | 687.431822 | -414.767796 |
| 98401 | 448226 | 184717 | 5528 | 2578 | franc | 2680.867996 | 5425.132004 | 54.988249 | -38.654713 | 1.689226e+05 | 4.640204e+05 | 679.566960 | -410.022464 |
| 124912 | 912074 | 790701 | 6807 | 11154 | jeune | 5940.176423 | 12020.823577 | 11.246854 | -7.906124 | 4.544441e+05 | 1.248331e+06 | 678.850449 | -409.590152 |
| 78923 | 359895 | 107364 | 2263 | 941 | décéder | 1059.647306 | 2144.352694 | 36.966835 | -25.986323 | 1.247042e+05 | 3.425548e+05 | 666.008794 | -401.842031 |
| 73775 | 590941 | 364820 | 5490 | 4893 | direct | 3433.931952 | 6949.068048 | 35.086629 | -24.664607 | 2.550777e+05 | 7.006833e+05 | 665.007040 | -401.237614 |
| 173822 | 1431598 | 1697788 | 9831 | 17126 | personne | 8915.390893 | 18041.609107 | 9.697056 | -6.816673 | 8.351844e+05 | 2.294202e+06 | 652.613954 | -393.760141 |
| 120928 | 380152 | 138639 | 858 | 725 | intensif | 523.539852 | 1059.460148 | 14.617379 | -10.275479 | 1.384572e+05 | 3.803338e+05 | 649.545234 | -391.908603 |
| 195021 | 473294 | 243486 | 4932 | 3638 | romand | 2834.325034 | 5735.674966 | 39.401556 | -27.697842 | 1.912974e+05 | 5.254826e+05 | 644.746929 | -389.013505 |
| 227224 | 210167 | 2483 | 274 | 36 | ttc | 102.525176 | 207.474824 | 16.934996 | -11.904678 | 5.675297e+04 | 1.558970e+05 | 643.977593 | -388.549319 |
| 94314 | 544054 | 330145 | 2799 | 2936 | fermer | 1896.715761 | 3838.284239 | 20.717734 | -14.563803 | 2.333101e+05 | 6.408889e+05 | 643.333016 | -388.160409 |
| 165668 | 323774 | 90897 | 1650 | 967 | ofsp | 865.510924 | 1751.489076 | 26.665555 | -18.744902 | 1.106692e+05 | 3.040018e+05 | 640.589351 | -386.504995 |
| 124880 | 603004 | 415228 | 6410 | 6085 | jeudi | 4132.426057 | 8362.573943 | 35.429901 | -24.905915 | 2.717503e+05 | 7.464817e+05 | 635.441821 | -383.399189 |
| 183502 | 564133 | 369689 | 6482 | 5235 | président | 3875.120937 | 7841.879063 | 41.877260 | -29.438170 | 2.492226e+05 | 6.845994e+05 | 630.802495 | -380.600013 |
| 164720 | 372285 | 151453 | 1565 | 2384 | obligatoire | 1306.038455 | 2642.961545 | 7.165678 | -5.037208 | 1.397775e+05 | 3.839605e+05 | 621.896731 | -375.226645 |
| 184074 | 871883 | 830637 | 7570 | 9067 | public | 5502.294702 | 11134.705298 | 27.875118 | -19.595181 | 4.543761e+05 | 1.248144e+06 | 619.378251 | -373.707098 |
| 33287 | 502293 | 313249 | 3246 | 2481 | autorité | 1894.069950 | 3832.930050 | 31.063917 | -21.836789 | 2.176555e+05 | 5.978865e+05 | 610.108944 | -368.114384 |
| 196104 | 188172 | 3914 | 313 | 15 | rtsavecvous | 108.478251 | 219.521749 | 19.636684 | -13.803866 | 5.126476e+04 | 1.408212e+05 | 604.667927 | -364.831500 |
| 89003 | 498105 | 316446 | 4935 | 4328 | etat | 3063.518412 | 6199.481588 | 33.812347 | -23.768834 | 2.173910e+05 | 5.971600e+05 | 602.064953 | -363.260974 |
| 25153 | 2087726 | 3109971 | 19230 | 31390 | an | 16741.369106 | 33878.630894 | 19.233796 | -13.520650 | 1.387184e+06 | 3.810513e+06 | 594.794351 | -358.874195 |
| 65290 | 712021 | 629921 | 9105 | 9634 | crise | 6197.481543 | 12541.518457 | 36.933023 | -25.962554 | 3.581434e+05 | 9.837986e+05 | 591.322702 | -356.779546 |
| 177866 | 751028 | 689665 | 4245 | 3516 | police | 2566.767397 | 5194.232603 | 33.125230 | -23.285816 | 3.844985e+05 | 1.056194e+06 | 591.100817 | -356.645670 |
| 6380 | 172467 | 1352 | 793 | 23 | 19h30rts | 269.872722 | 546.127278 | 31.844019 | -22.385172 | 4.638958e+04 | 1.274294e+05 | 585.365410 | -353.185164 |
| 163242 | 183003 | 9753 | 391 | 45 | nouvo | 144.196700 | 291.803300 | 20.552909 | -14.447938 | 5.144357e+04 | 1.413124e+05 | 580.037933 | -349.970785 |
| 133797 | 495278 | 344297 | 5699 | 4732 | lancer | 3449.806818 | 6981.193182 | 38.293880 | -26.919186 | 2.240695e+05 | 6.155055e+05 | 572.943687 | -345.690412 |
| 208647 | 431379 | 264286 | 3224 | 4850 | société | 2670.284752 | 5403.715248 | 10.715383 | -7.532519 | 1.856622e+05 | 5.100028e+05 | 570.260425 | -344.071443 |
fig = px.bar(graph_interactions_media1, x="res_inter_media", y="mot", labels={"res_inter_media":"Résiduel de Pearson (<b>en fonction des interactions</b>)","mot":"Lemme (dans les posts Facebook <b>médias</b>)"}, orientation="h", title="Lemmes les plus caractéristiques des posts Facebook <b>médias</b> {} en 2020<br>(en fonction des interactions suscitées)".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="gold", opacity=0.75, textfont_size=12)
fig
graph_interactions_nonmedia1 = khi2_1.sort_values(by=["res_inter_nonmedia"],ascending=False).head(50)
graph_interactions_nonmedia1
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | mot | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174900 | 299280 | 7716498 | 3976 | 55597 | photo | 19702.362342 | 39870.637658 | -112.038975 | 78.759271 | 2.139286e+06 | 5.876492e+06 | -1258.012219 | 759.032297 |
| 222630 | 15728 | 4913467 | 428 | 20718 | timeline | 6993.539927 | 14152.460073 | -78.509447 | 55.189248 | 1.315525e+06 | 3.613670e+06 | -1133.250825 | 683.756456 |
| 217787 | 170705 | 3092510 | 3153 | 12351 | série | 5127.581719 | 10376.418281 | -27.575209 | 19.384356 | 8.709013e+05 | 2.392314e+06 | -750.300665 | 452.700243 |
| 73075 | 14190 | 2196616 | 237 | 3878 | dieu | 1360.939033 | 2754.060967 | -30.466560 | 21.416869 | 5.900297e+05 | 1.620776e+06 | -749.660564 | 452.314032 |
| 65945 | 43053 | 2322400 | 1053 | 1708 | crédit | 913.135522 | 1847.864478 | 4.628495 | -3.253662 | 6.313026e+05 | 1.734150e+06 | -740.359820 | 446.702350 |
| 99564 | 70893 | 2086825 | 1191 | 12900 | from | 4660.265351 | 9430.734649 | -50.819712 | 35.724385 | 5.758613e+05 | 1.581857e+06 | -665.434305 | 401.495408 |
| 22946 | 0 | 1568544 | 0 | 2720 | alffr | 899.575740 | 1820.424260 | -29.992928 | 21.083923 | 4.186200e+05 | 1.149924e+06 | -647.008477 | 390.378029 |
| 210670 | 4497 | 1572818 | 19 | 2014 | souviens | 672.366721 | 1360.633279 | -25.197294 | 17.712769 | 4.209608e+05 | 1.156354e+06 | -641.883831 | 387.286031 |
| 227730 | 49609 | 1674101 | 714 | 3513 | tv | 1397.980387 | 2829.019613 | -18.293344 | 12.859547 | 4.600314e+05 | 1.263679e+06 | -605.114129 | 365.100720 |
| 117418 | 238388 | 2477715 | 2116 | 6755 | image | 2933.873673 | 5937.126327 | -15.099603 | 10.614464 | 7.248856e+05 | 1.991217e+06 | -571.407537 | 344.763563 |
| 24895 | 51410 | 1508070 | 708 | 13768 | amour | 4787.595006 | 9688.404994 | -58.960119 | 41.446791 | 4.162009e+05 | 1.143279e+06 | -565.447786 | 341.167697 |
| 179062 | 195944 | 2173828 | 1893 | 14551 | post | 5438.464512 | 11005.535488 | -48.076738 | 33.796175 | 6.324552e+05 | 1.737317e+06 | -548.883958 | 331.173772 |
| 38238 | 148809 | 1942899 | 1969 | 11751 | bel | 4537.565866 | 9182.434134 | -38.131091 | 26.804752 | 5.582443e+05 | 1.533464e+06 | -547.990628 | 330.634774 |
| 202576 | 4183 | 1065822 | 155 | 1469 | schweiz | 537.099633 | 1086.900367 | -16.487287 | 11.589955 | 2.855677e+05 | 7.844373e+05 | -526.557638 | 317.702998 |
| 71798 | 61140 | 1354898 | 869 | 3227 | dessin | 1354.655232 | 2741.344768 | -13.195130 | 9.275690 | 3.779185e+05 | 1.038120e+06 | -515.295816 | 310.908083 |
| 216926 | 15744 | 1072319 | 267 | 2735 | switzerland | 992.840578 | 2009.159422 | -23.035704 | 16.193251 | 2.903871e+05 | 7.976759e+05 | -509.659366 | 307.507283 |
| 190096 | 24114 | 1091458 | 372 | 3153 | regarder | 1165.810472 | 2359.189528 | -23.248923 | 16.343137 | 2.977288e+05 | 8.178432e+05 | -501.451758 | 302.555153 |
| 78831 | 409877 | 2873301 | 5611 | 46373 | découvrir | 17192.479882 | 34791.520118 | -88.327267 | 62.090814 | 8.762291e+05 | 2.406949e+06 | -498.201569 | 300.594124 |
| 109410 | 6991 | 924771 | 75 | 1194 | générique | 419.691770 | 849.308230 | -16.825411 | 11.827644 | 2.486728e+05 | 6.830892e+05 | -484.651740 | 292.418720 |
| 210644 | 48791 | 1161140 | 886 | 2912 | souvenir | 1256.098773 | 2541.901227 | -10.442530 | 7.340714 | 3.229117e+05 | 8.870193e+05 | -482.391872 | 291.055210 |
| 201406 | 266828 | 2108996 | 3333 | 19568 | savoir | 7573.964716 | 15327.035284 | -48.730742 | 34.255916 | 6.340704e+05 | 1.741754e+06 | -461.194483 | 278.265586 |
| 191137 | 6282 | 828420 | 93 | 1334 | renaud | 471.946537 | 955.053463 | -17.443416 | 12.262079 | 2.227690e+05 | 6.119330e+05 | -458.674303 | 276.745015 |
| 153697 | 190183 | 1748089 | 1568 | 2376 | montagne | 1304.384823 | 2639.615177 | 7.299070 | -5.130977 | 5.172946e+05 | 1.420977e+06 | -454.806840 | 274.411548 |
| 89100 | 2038 | 783724 | 6 | 762 | eternel | 253.997856 | 514.002144 | -15.560835 | 10.938694 | 2.097076e+05 | 5.760544e+05 | -453.488091 | 273.615869 |
| 57464 | 513 | 763227 | 15 | 915 | clique | 307.575529 | 622.424471 | -16.682537 | 11.727209 | 2.038303e+05 | 5.599097e+05 | -450.339433 | 271.716100 |
| 11018 | 1469 | 768904 | 77 | 4473 | 3 | 1504.805007 | 3045.194993 | -36.806861 | 25.873867 | 2.056006e+05 | 5.647724e+05 | -450.192241 | 271.627291 |
| 16018 | 80295 | 1198533 | 910 | 3646 | 80 | 1506.789365 | 3049.210635 | -15.374281 | 10.807553 | 3.412993e+05 | 9.375287e+05 | -446.765824 | 269.559933 |
| 143287 | 25081 | 891252 | 374 | 4106 | magnifique | 1481.654160 | 2998.345840 | -28.776022 | 20.228483 | 2.445550e+05 | 6.717780e+05 | -443.807683 | 267.775113 |
| 37717 | 17331 | 837722 | 365 | 2182 | beauté | 842.360077 | 1704.639923 | -16.447398 | 11.561915 | 2.282003e+05 | 6.268527e+05 | -441.423333 | 266.336496 |
| 183743 | 0 | 726335 | 0 | 659 | psaume | 217.948681 | 441.051319 | -14.763085 | 10.377905 | 1.938475e+05 | 5.324875e+05 | -440.281162 | 265.647357 |
| 216399 | 403 | 726150 | 18 | 594 | svizzera | 202.404542 | 409.595458 | -12.961686 | 9.111587 | 1.939057e+05 | 5.326473e+05 | -439.432043 | 265.135034 |
| 157113 | 36758 | 937320 | 437 | 1571 | mythique | 664.098561 | 1343.901439 | -8.812479 | 6.194848 | 2.599663e+05 | 7.141117e+05 | -437.775808 | 264.135731 |
| 216943 | 0 | 714137 | 0 | 414 | switzerlandpicture | 136.920719 | 277.079281 | -11.701313 | 8.225592 | 1.905920e+05 | 5.235450e+05 | -436.568489 | 263.407285 |
| 132945 | 1458 | 703460 | 5 | 395 | lacleman | 132.290550 | 267.709450 | -11.067047 | 7.779726 | 1.881316e+05 | 5.167864e+05 | -430.379992 | 259.673403 |
| 125425 | 7511 | 729543 | 90 | 1838 | johnny | 637.640451 | 1290.359549 | -21.687405 | 15.245447 | 1.967082e+05 | 5.403458e+05 | -426.582972 | 257.382439 |
| 248831 | 292681 | 2070334 | 3042 | 17399 | être | 6760.377833 | 13680.622167 | -45.223902 | 31.790737 | 6.306519e+05 | 1.732363e+06 | -425.583187 | 256.779210 |
| 174128 | 589430 | 3220373 | 5981 | 18285 | petit | 8025.406218 | 16240.593782 | -22.820948 | 16.042286 | 1.016777e+06 | 2.793026e+06 | -423.806761 | 255.707389 |
| 110243 | 5544 | 704174 | 37 | 4854 | hallyday | 1617.582700 | 3273.417300 | -39.299224 | 27.625907 | 1.894127e+05 | 5.203053e+05 | -422.477162 | 254.905164 |
| 33925 | 200723 | 1662537 | 2358 | 10967 | avoir | 4406.928948 | 8918.071052 | -30.864474 | 21.696588 | 4.972751e+05 | 1.365985e+06 | -420.535465 | 253.733625 |
| 237433 | 193748 | 1629315 | 2696 | 14725 | vous | 5761.584180 | 11659.415820 | -40.387065 | 28.390618 | 4.865471e+05 | 1.336516e+06 | -419.766061 | 253.269398 |
| 157097 | 25 | 656440 | 2 | 430 | myswitzerland | 142.873794 | 289.126206 | -11.785660 | 8.284885 | 1.752003e+05 | 4.812647e+05 | -418.509606 | 252.511305 |
| 25987 | 13399 | 736164 | 238 | 1836 | animer | 685.926502 | 1388.073498 | -17.102830 | 12.022659 | 2.000467e+05 | 5.495163e+05 | -417.308219 | 251.786438 |
| 190095 | 13655 | 736469 | 87 | 1078 | regarde | 385.296227 | 779.703773 | -15.196738 | 10.682747 | 2.001964e+05 | 5.499276e+05 | -416.914614 | 251.548954 |
| 43231 | 639731 | 3370363 | 6748 | 20734 | bon | 9089.022240 | 18392.977760 | -24.555397 | 17.261539 | 1.070232e+06 | 2.939862e+06 | -416.135641 | 251.078954 |
| 163636 | 16910 | 749257 | 169 | 246 | nuage | 137.251446 | 277.748554 | 2.709976 | -1.905013 | 2.044780e+05 | 5.616890e+05 | -414.796904 | 250.271215 |
| 226889 | 562 | 611242 | 28 | 265 | trust | 96.902828 | 196.097172 | -6.999529 | 4.920411 | 1.632810e+05 | 4.485230e+05 | -402.689577 | 242.966157 |
| 116815 | 153 | 608039 | 6 | 272 | ig | 91.941932 | 186.058068 | -8.962895 | 6.300585 | 1.623170e+05 | 4.458750e+05 | -402.506048 | 242.855423 |
| 55360 | 72844 | 1007386 | 1211 | 7006 | chose | 2717.578624 | 5499.421376 | -28.900193 | 20.315771 | 2.882966e+05 | 7.919334e+05 | -401.265607 | 242.106993 |
| 203722 | 4808 | 615966 | 45 | 876 | seigneur | 304.598991 | 616.401009 | -14.874377 | 10.456139 | 1.656749e+05 | 4.550991e+05 | -395.219491 | 238.459018 |
| 209021 | 65868 | 946456 | 861 | 2552 | soleil | 1128.769118 | 2284.230882 | -7.969993 | 5.602611 | 2.701735e+05 | 7.421505e+05 | -393.059865 | 237.155989 |
fig = px.bar(graph_interactions_nonmedia1, x="res_inter_nonmedia", y="mot", labels={"res_inter_nonmedia":"Résiduel de Pearson (<b>en fonction des interactions</b>)","mot":"Lemme (dans les posts Facebook <b>non-médias</b>)"}, orientation="h", title="Lemmes les plus caractéristiques des posts Facebook <b>non-médias</b> {} en 2020<br>(en fonction des interactions suscitées)".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="lightyellow", opacity=0.75, textfont_size=12)
fig
media2 = pan.read_csv("suisse-bigrammes-media-nettoye.csv", low_memory=False, names=["bigramme","interactions"])
nonmedia2 = pan.read_csv("suisse-bigrammes-nonmedia-nettoye.csv", low_memory=False, names=["bigramme","interactions"])
media2
| bigramme | interactions | |
|---|---|---|
| 0 | donner enfant | 49596 |
| 1 | enfant envie | 49596 |
| 2 | envie intéresser | 49596 |
| 3 | intéresser biodiversité | 49596 |
| 4 | biodiversité falloir | 49596 |
| ... | ... | ... |
| 4242484 | complétez formulaire | 0 |
| 4242485 | formulaire ici | 0 |
| 4242486 | ici jardinière | 0 |
| 4242487 | jardinière recruter | 0 |
| 4242488 | recruter rtn | 0 |
4242489 rows × 2 columns
nonmedia2
| bigramme | interactions | |
|---|---|---|
| 0 | falloir il | 107933 |
| 1 | il faire | 107933 |
| 2 | faire petit | 107933 |
| 3 | petit prince | 107933 |
| 4 | prince falloir | 107933 |
| ... | ... | ... |
| 8612244 | indipendentemente dal | 0 |
| 8612245 | dal tuo | 0 |
| 8612246 | tuo background | 0 |
| 8612247 | background maggiori | 0 |
| 8612248 | maggiori informazioni | 0 |
8612249 rows × 2 columns
media2_table = pan.pivot_table(media2,index=["bigramme"],values=["bigramme","interactions"],aggfunc=[len,np.sum])
nonmedia2_table = pan.pivot_table(nonmedia2,index=["bigramme"],values=["bigramme","interactions"],aggfunc=[len,np.sum])
media2_table
| len | sum | |
|---|---|---|
| interactions | interactions | |
| bigramme | ||
| #12h45rts chine | 1 | 179 |
| #19h30rt crèches | 1 | 5 |
| #19h30rt rtsinfo | 1 | 10 |
| #coronaviru déclarer | 1 | 325 |
| #couleurslocales romandise | 1 | 74 |
| ... | ... | ... |
| 수원 이동국 | 1 | 8 |
| 시즌 k리그 | 1 | 8 |
| 이동국 덕분에챌린지 | 1 | 8 |
| 이동국의 시즌 | 1 | 8 |
| 전북 수원 | 1 | 8 |
1673277 rows × 2 columns
nonmedia2_table
| len | sum | |
|---|---|---|
| interactions | interactions | |
| bigramme | ||
| #111 disposition | 1 | 5 |
| #6 ski | 1 | 1 |
| #7 surf | 1 | 36 |
| #allezlausanne lswil | 1 | 105 |
| #allezxamax mafamille | 1 | 48 |
| ... | ... | ... |
| samedi cavelescretet | 1 | 43 |
| sea dahu | 3 | 30 |
| sen ira | 1 | 0 |
| sonore des | 1 | 0 |
| spontanes cie | 2 | 0 |
2796740 rows × 2 columns
media2_table["type"] = "media"
nonmedia2_table["type"] = "non-media"
media2_table
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| bigramme | |||
| #12h45rts chine | 1 | 179 | media |
| #19h30rt crèches | 1 | 5 | media |
| #19h30rt rtsinfo | 1 | 10 | media |
| #coronaviru déclarer | 1 | 325 | media |
| #couleurslocales romandise | 1 | 74 | media |
| ... | ... | ... | ... |
| 수원 이동국 | 1 | 8 | media |
| 시즌 k리그 | 1 | 8 | media |
| 이동국 덕분에챌린지 | 1 | 8 | media |
| 이동국의 시즌 | 1 | 8 | media |
| 전북 수원 | 1 | 8 | media |
1673277 rows × 3 columns
nonmedia2_table
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| bigramme | |||
| #111 disposition | 1 | 5 | non-media |
| #6 ski | 1 | 1 | non-media |
| #7 surf | 1 | 36 | non-media |
| #allezlausanne lswil | 1 | 105 | non-media |
| #allezxamax mafamille | 1 | 48 | non-media |
| ... | ... | ... | ... |
| samedi cavelescretet | 1 | 43 | non-media |
| sea dahu | 3 | 30 | non-media |
| sen ira | 1 | 0 | non-media |
| sonore des | 1 | 0 | non-media |
| spontanes cie | 2 | 0 | non-media |
2796740 rows × 3 columns
tableau2 = pan.concat([media2_table,nonmedia2_table], names = ["bigramme","nb","interactions","type"], levels=0)
tableau2
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| bigramme | |||
| #12h45rts chine | 1 | 179 | media |
| #19h30rt crèches | 1 | 5 | media |
| #19h30rt rtsinfo | 1 | 10 | media |
| #coronaviru déclarer | 1 | 325 | media |
| #couleurslocales romandise | 1 | 74 | media |
| ... | ... | ... | ... |
| samedi cavelescretet | 1 | 43 | non-media |
| sea dahu | 3 | 30 | non-media |
| sen ira | 1 | 0 | non-media |
| sonore des | 1 | 0 | non-media |
| spontanes cie | 2 | 0 | non-media |
4470017 rows × 3 columns
tableau2["bigramme"] = tableau2.index
tableau2.columns = ["nb","interactions","media","bigramme"]
tableau2.reset_index(drop=True, inplace=True)
tableau2
| nb | interactions | media | bigramme | |
|---|---|---|---|---|
| 0 | 1 | 179 | media | #12h45rts chine |
| 1 | 1 | 5 | media | #19h30rt crèches |
| 2 | 1 | 10 | media | #19h30rt rtsinfo |
| 3 | 1 | 325 | media | #coronaviru déclarer |
| 4 | 1 | 74 | media | #couleurslocales romandise |
| ... | ... | ... | ... | ... |
| 4470012 | 1 | 43 | non-media | samedi cavelescretet |
| 4470013 | 3 | 30 | non-media | sea dahu |
| 4470014 | 1 | 0 | non-media | sen ira |
| 4470015 | 1 | 0 | non-media | sonore des |
| 4470016 | 2 | 0 | non-media | spontanes cie |
4470017 rows × 4 columns
khi2_2 = pan.pivot_table(tableau2,index=["bigramme"],columns=["media"],values=["bigramme","interactions"],aggfunc=[len,np.sum],fill_value=0)
khi2_2
| len | sum | |||||||
|---|---|---|---|---|---|---|---|---|
| interactions | nb | interactions | nb | |||||
| media | media | non-media | media | non-media | media | non-media | media | non-media |
| bigramme | ||||||||
| #111 disposition | 0 | 1 | 0 | 1 | 0 | 5 | 0 | 1 |
| #12h45rts chine | 1 | 0 | 1 | 0 | 179 | 0 | 1 | 0 |
| #19h30rt crèches | 1 | 0 | 1 | 0 | 5 | 0 | 1 | 0 |
| #19h30rt rtsinfo | 1 | 0 | 1 | 0 | 10 | 0 | 1 | 0 |
| #6 ski | 0 | 1 | 0 | 1 | 0 | 1 | 0 | 1 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... |
| samedi cavelescretet | 0 | 1 | 0 | 1 | 0 | 43 | 0 | 1 |
| sea dahu | 0 | 1 | 0 | 1 | 0 | 30 | 0 | 3 |
| sen ira | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 1 |
| sonore des | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 1 |
| spontanes cie | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 2 |
4023862 rows × 8 columns
khi2_2["bigramme"] = khi2_2.index
khi2_2.columns = khi2_2.columns.get_level_values(0)
khi2_2.reset_index(drop=True, inplace=True)
khi2_2.columns = ["a","b","c","d","interactions_media","interactions_nonmedia","obs_media","obs_nonmedia","bigramme"]
khi2_2 = khi2_2.drop(columns=["a","b","c","d"])
khi2_2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | |
|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo |
| 4 | 0 | 1 | 0 | 1 | #6 ski |
| ... | ... | ... | ... | ... | ... |
| 4023857 | 0 | 43 | 0 | 1 | samedi cavelescretet |
| 4023858 | 0 | 30 | 0 | 3 | sea dahu |
| 4023859 | 0 | 0 | 0 | 1 | sen ira |
| 4023860 | 0 | 0 | 0 | 1 | sonore des |
| 4023861 | 0 | 0 | 0 | 2 | spontanes cie |
4023862 rows × 5 columns
khi2_2.obs_media.sum(), khi2_2.obs_nonmedia.sum()
(4242489, 8612249)
print("Nb de lignes fichier media2 = ", media2.shape[0])
print("Somme observée média khi2_2 = ", khi2_2.obs_media.sum())
print("Nb de lignes fichier nonmedia2 = ", nonmedia2.shape[0])
print("Somme observée nonmédia khi2_2 = ", khi2_2.obs_nonmedia.sum())
Nb de lignes fichier media2 = 4242489 Somme observée média khi2_2 = 4242489 Nb de lignes fichier nonmedia2 = 8612249 Somme observée nonmédia khi2_2 = 8612249
khi2_2["exp_media"] = ((khi2_2.obs_media + khi2_2.obs_nonmedia) * khi2_2.obs_media.sum()) / (khi2_2.obs_media.sum() +khi2_2.obs_nonmedia.sum())
khi2_2["exp_nonmedia"] = ((khi2_2.obs_media + khi2_2.obs_nonmedia) * khi2_2.obs_nonmedia.sum()) / (khi2_2.obs_media.sum() +khi2_2.obs_nonmedia.sum())
khi2_2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | |
|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition | 0.330033 | 0.669967 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine | 0.330033 | 0.669967 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches | 0.330033 | 0.669967 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo | 0.330033 | 0.669967 |
| 4 | 0 | 1 | 0 | 1 | #6 ski | 0.330033 | 0.669967 |
| ... | ... | ... | ... | ... | ... | ... | ... |
| 4023857 | 0 | 43 | 0 | 1 | samedi cavelescretet | 0.330033 | 0.669967 |
| 4023858 | 0 | 30 | 0 | 3 | sea dahu | 0.990099 | 2.009901 |
| 4023859 | 0 | 0 | 0 | 1 | sen ira | 0.330033 | 0.669967 |
| 4023860 | 0 | 0 | 0 | 1 | sonore des | 0.330033 | 0.669967 |
| 4023861 | 0 | 0 | 0 | 2 | spontanes cie | 0.660066 | 1.339934 |
4023862 rows × 7 columns
khi2_2["res_media"] = (khi2_2.obs_media - khi2_2.exp_media) / np.sqrt(khi2_2.exp_media)
khi2_2["res_nonmedia"] = (khi2_2.obs_nonmedia - khi2_2.exp_nonmedia) / np.sqrt(khi2_2.exp_nonmedia)
khi2_2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition | 0.330033 | 0.669967 | -0.574485 | 0.403210 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine | 0.330033 | 0.669967 | 1.166204 | -0.818515 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches | 0.330033 | 0.669967 | 1.166204 | -0.818515 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo | 0.330033 | 0.669967 | 1.166204 | -0.818515 |
| 4 | 0 | 1 | 0 | 1 | #6 ski | 0.330033 | 0.669967 | -0.574485 | 0.403210 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 4023857 | 0 | 43 | 0 | 1 | samedi cavelescretet | 0.330033 | 0.669967 | -0.574485 | 0.403210 |
| 4023858 | 0 | 30 | 0 | 3 | sea dahu | 0.990099 | 2.009901 | -0.995037 | 0.698379 |
| 4023859 | 0 | 0 | 0 | 1 | sen ira | 0.330033 | 0.669967 | -0.574485 | 0.403210 |
| 4023860 | 0 | 0 | 0 | 1 | sonore des | 0.330033 | 0.669967 | -0.574485 | 0.403210 |
| 4023861 | 0 | 0 | 0 | 2 | spontanes cie | 0.660066 | 1.339934 | -0.812445 | 0.570224 |
4023862 rows × 9 columns
graph_media2 = khi2_2.sort_values(by=["res_media"],ascending=False).head(50)
graph_media2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 3471275 | 243252 | 6291 | 3765 | 124 | suisse monde | 1283.498716 | 2605.501284 | 69.265470 | -48.614840 |
| 949395 | 392132 | 6995 | 3530 | 133 | coronavirus suisse | 1208.911236 | 2454.088764 | 66.756651 | -46.853994 |
| 4010276 | 185290 | 408 | 2250 | 20 | évolution coronavirus | 749.175131 | 1520.824869 | 54.832537 | -38.484905 |
| 642364 | 43477 | 16896 | 2392 | 374 | canal alpha | 912.871548 | 1853.128452 | 48.955451 | -34.359998 |
| 3342541 | 159429 | 1719 | 1786 | 14 | site app | 594.059576 | 1205.940424 | 48.903456 | -34.323504 |
| 338814 | 134019 | 37 | 1464 | 2 | app évolution | 483.828521 | 982.171479 | 44.561144 | -31.275798 |
| 3094039 | 118892 | 666 | 1448 | 5 | restezchezvous coronavirus | 479.538091 | 973.461909 | 44.225321 | -31.040097 |
| 3478120 | 181028 | 5939 | 1857 | 294 | suivre direct | 709.901193 | 1441.098807 | 43.052847 | -30.217181 |
| 1761699 | 34516 | 8125 | 1502 | 126 | hockey glace | 537.293883 | 1090.706117 | 41.618755 | -29.210646 |
| 1112001 | 129332 | 1473 | 1325 | 33 | direct site | 448.184946 | 909.815054 | 41.417069 | -29.069090 |
| 900227 | 814330 | 271088 | 4713 | 3257 | conseil fédéral | 2630.363787 | 5339.636213 | 40.607430 | -28.500835 |
| 2301805 | 110638 | 34678 | 2200 | 686 | million franc | 952.475519 | 1933.524481 | 40.422407 | -28.370974 |
| 2480943 | 386653 | 20836 | 1613 | 265 | nouveau cas | 619.802157 | 1258.197843 | 39.894151 | -28.000211 |
| 1461283 | 87414 | 115840 | 1928 | 966 | fc sion | 955.115784 | 1938.884216 | 31.479886 | -22.094553 |
| 95344 | 275062 | 60164 | 1282 | 423 | 24 heure | 562.706431 | 1142.293569 | 30.322516 | -21.282239 |
| 2004782 | 29725 | 5413 | 799 | 77 | jura bernois | 289.108993 | 586.891007 | 29.987934 | -21.047408 |
| 2217156 | 48313 | 14078 | 881 | 135 | mardi soir | 335.313627 | 680.686373 | 29.800085 | -20.915564 |
| 2425935 | 21570 | 16317 | 924 | 169 | national league | 360.726176 | 732.273824 | 29.657241 | -20.815307 |
| 3482191 | 26040 | 25202 | 1051 | 265 | super league | 434.323556 | 881.676444 | 29.590388 | -20.768386 |
| 3102718 | 41001 | 12169 | 934 | 181 | retrouver ici | 367.986904 | 747.013096 | 29.505997 | -20.709155 |
| 241871 | 227955 | 70029 | 973 | 225 | alain berset | 395.379651 | 802.620349 | 29.049277 | -20.388600 |
| 3350212 | 41818 | 3756 | 767 | 86 | ski alpin | 281.518232 | 571.481768 | 28.934745 | -20.308214 |
| 962868 | 39281 | 15604 | 993 | 246 | coupe monde | 408.911008 | 830.088992 | 28.884484 | -20.272938 |
| 1148401 | 184281 | 52439 | 1924 | 1136 | donald trump | 1009.901278 | 2050.098722 | 28.764289 | -20.188577 |
| 237383 | 5952 | 1441 | 639 | 20 | air temps | 217.491811 | 441.508189 | 28.581470 | -20.060264 |
| 2092813 | 110377 | 27516 | 1026 | 288 | lier coronavirus | 433.663490 | 880.336510 | 28.444092 | -19.963843 |
| 982615 | 70332 | 5249 | 700 | 72 | covid-19 suisse | 254.785551 | 517.214449 | 27.892141 | -19.576449 |
| 2335608 | 22272 | 7143 | 706 | 78 | monde coronavirus | 258.745948 | 525.254052 | 27.804655 | -19.515046 |
| 2444679 | 30942 | 22590 | 918 | 231 | neuchâtel xamax | 379.208029 | 769.791971 | 27.668292 | -19.419338 |
| 2983365 | 18751 | 4440 | 775 | 128 | radio lac | 298.019887 | 604.980113 | 27.629794 | -19.392318 |
| 2750359 | 17258 | 4764 | 655 | 59 | play off | 235.643632 | 478.356368 | 27.318408 | -19.173768 |
| 1974336 | 117232 | 14779 | 973 | 290 | joe biden | 416.831802 | 846.168198 | 27.241168 | -19.119556 |
| 2354798 | 20730 | 420 | 541 | 2 | montreux mymontreuxch | 179.207972 | 363.792028 | 27.025910 | -18.968474 |
| 2451144 | 20335 | 0 | 536 | 0 | news commune | 176.897740 | 359.102260 | 26.999579 | -18.949994 |
| 3617039 | 16214 | 3533 | 650 | 65 | tour france | 235.973665 | 479.026335 | 26.952323 | -18.916826 |
| 650614 | 176976 | 67851 | 1420 | 738 | canton vaud | 712.211424 | 1445.788576 | 26.521561 | -18.614491 |
| 838918 | 21668 | 1496 | 554 | 29 | commune montreux | 192.409296 | 390.590704 | 26.067791 | -18.296006 |
| 3757896 | 63374 | 15485 | 771 | 198 | vendredi soir | 319.802072 | 649.197928 | 25.230535 | -17.708368 |
| 900128 | 213881 | 101114 | 1968 | 1461 | conseil etat | 1131.683491 | 2297.316509 | 24.860404 | -17.448587 |
| 962994 | 46928 | 25888 | 868 | 290 | coupe suisse | 382.178327 | 775.821673 | 24.850999 | -17.441986 |
| 2547508 | 16595 | 242 | 471 | 11 | open australie | 159.075953 | 322.924047 | 24.731280 | -17.357959 |
| 3986113 | 23367 | 9984 | 625 | 107 | équipe suisse | 241.584227 | 490.415773 | 24.668099 | -17.313615 |
| 4010287 | 14902 | 255 | 441 | 7 | évolution covid-19 | 147.854828 | 300.145172 | 24.108211 | -16.920651 |
| 1673063 | 1849 | 1721 | 459 | 17 | grand étape | 157.095754 | 318.904246 | 24.087238 | -16.905930 |
| 2528375 | 223949 | 64841 | 1182 | 620 | office fédéral | 594.719642 | 1207.280358 | 24.081822 | -16.902129 |
| 2596245 | 129779 | 94033 | 1602 | 1084 | pandémie coronavirus | 886.468900 | 1799.531100 | 24.032379 | -16.867427 |
| 3573796 | 153529 | 62319 | 1136 | 585 | tester positif | 567.986961 | 1153.013039 | 23.833571 | -16.727891 |
| 2920496 | 77687 | 8712 | 653 | 151 | président américain | 265.346610 | 538.653390 | 23.797800 | -16.702785 |
| 948060 | 25314 | 10051 | 542 | 74 | coronavirus nouveau | 203.300388 | 412.699612 | 23.754484 | -16.672383 |
| 2983378 | 14534 | 453 | 429 | 8 | radio lfm | 144.224464 | 292.775536 | 23.712820 | -16.643141 |
fig = px.bar(graph_media2, x="res_media", y="bigramme", labels={"res_media":"Résiduel de Pearson","bigramme":"Bigramme (dans les posts Facebook <b>médias</b>)"}, orientation="h", title="Bigrammes les plus caractéristiques des posts Facebook <b>médias</b> {} en 2020".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="navy", opacity=0.75, textfont_size=12)
fig
graph_nonmedia2 = khi2_2.sort_values(by=["res_nonmedia"],ascending=False).head(50)
graph_nonmedia2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 3594105 | 15577 | 4542299 | 420 | 20376 | timeline photo | 6863.368296 | 13932.631704 | -77.775767 | 54.587899 |
| 3329168 | 29 | 9351 | 7 | 9610 | signe horoscope | 3173.928299 | 6443.071701 | -56.213377 | 39.454064 |
| 2030558 | 31334 | 16052 | 37 | 8792 | koh lanta | 2913.862218 | 5915.137782 | -53.294766 | 37.405600 |
| 2710373 | 63129 | 1854100 | 1029 | 10642 | photo from | 3851.816281 | 7819.183719 | -45.483076 | 31.922868 |
| 78602 | 382 | 7128 | 16 | 5366 | 2020 savoir | 1776.238131 | 3605.761869 | -41.765802 | 29.313853 |
| 3263658 | 40 | 5668 | 3 | 5282 | savoir journée | 1744.224920 | 3540.775080 | -41.692087 | 29.262114 |
| 218804 | 0 | 7505 | 0 | 4457 | agathe auproux | 1470.957516 | 2986.042484 | -38.353064 | 26.918580 |
| 3328866 | 4 | 11729 | 2 | 3988 | signe astrologique | 1316.832059 | 2673.167941 | -36.233066 | 25.430633 |
| 1205092 | 381 | 54093 | 11 | 3752 | découvrir recette | 1241.914546 | 2521.085454 | -34.928670 | 24.515125 |
| 670484 | 2395 | 14719 | 25 | 3789 | casa papel | 1258.746234 | 2555.253766 | -34.774168 | 24.406686 |
| 3329609 | 5 | 4243 | 1 | 3307 | signe zodiaque | 1091.749487 | 2216.250513 | -33.011368 | 23.169443 |
| 78501 | 22 | 3161 | 1 | 3174 | 2020 réserve | 1047.855085 | 2127.144915 | -32.339698 | 22.698023 |
| 3201351 | 266 | 5206 | 6 | 3043 | réserve surprise | 1006.270914 | 2042.729086 | -31.532629 | 22.131572 |
| 1203954 | 128 | 3149 | 33 | 2968 | découvrir horoscope | 990.429326 | 2010.570674 | -30.422506 | 21.352418 |
| 3011581 | 165 | 41872 | 6 | 2834 | recette facile | 937.293997 | 1902.706003 | -30.419277 | 21.350151 |
| 2906273 | 0 | 2501 | 0 | 2797 | prédire astre | 923.102574 | 1873.897426 | -30.382603 | 21.324411 |
| 4014678 | 0 | 2511 | 0 | 2777 | être capricorne | 916.501912 | 1860.498088 | -30.273783 | 21.248034 |
| 3795090 | 0 | 2511 | 0 | 2777 | vierge scorpion | 916.501912 | 1860.498088 | -30.273783 | 21.248034 |
| 656523 | 0 | 2511 | 0 | 2777 | capricorne vierge | 916.501912 | 1860.498088 | -30.273783 | 21.248034 |
| 1205374 | 9 | 6219 | 1 | 2728 | découvrir signe | 900.660323 | 1828.339677 | -29.977682 | 21.040213 |
| 3277501 | 0 | 2417 | 0 | 2717 | scorpion journée | 896.699926 | 1820.300074 | -29.944948 | 21.017238 |
| 402713 | 0 | 2268 | 0 | 2597 | astre être | 857.095954 | 1739.904046 | -29.276201 | 20.547869 |
| 3250639 | 162 | 3810 | 1 | 2588 | santé découvrir | 854.455689 | 1734.544311 | -29.196864 | 20.492185 |
| 78022 | 0 | 2200 | 0 | 2557 | 2020 prédire | 843.894630 | 1713.105370 | -29.049865 | 20.389012 |
| 282451 | 1 | 11722 | 1 | 2527 | amour argent | 834.323671 | 1693.676329 | -28.850041 | 20.248764 |
| 366488 | 0 | 4494 | 0 | 2519 | argent santé | 831.353373 | 1687.646627 | -28.833199 | 20.236943 |
| 1991943 | 0 | 2709 | 0 | 2464 | journée amour | 813.201552 | 1650.798448 | -28.516689 | 20.014796 |
| 1774500 | 67 | 3728 | 16 | 2424 | horoscope jour | 805.280758 | 1634.719242 | -27.813642 | 19.521354 |
| 2986908 | 0 | 42420 | 0 | 2295 | raison adopter | 757.425959 | 1537.574041 | -27.521373 | 19.316221 |
| 2710619 | 2624 | 7832 | 6 | 2251 | photo instagram | 744.884701 | 1512.115299 | -27.072736 | 19.001340 |
| 1986171 | 51 | 3531 | 4 | 2214 | jour gratuit | 732.013410 | 1485.986590 | -26.907903 | 18.885650 |
| 2678669 | 490 | 8518 | 14 | 2242 | perdre poids | 744.554668 | 1511.445332 | -26.773455 | 18.791286 |
| 2696497 | 0 | 213059 | 0 | 2116 | pet alert | 698.350034 | 1417.649966 | -26.426313 | 18.547640 |
| 1202766 | 83 | 286464 | 2 | 2110 | découvrir avenir | 697.029902 | 1414.970098 | -26.325570 | 18.476932 |
| 1027908 | 6479 | 40081 | 52 | 2316 | céline dion | 781.518375 | 1586.481625 | -26.095561 | 18.315497 |
| 2176130 | 7811 | 73532 | 161 | 2796 | mai 2020 | 975.907869 | 1981.092131 | -26.085796 | 18.308644 |
| 1931659 | 0 | 2532 | 0 | 1970 | inès loucif | 650.165202 | 1319.834798 | -25.498337 | 17.896328 |
| 2227198 | 17600 | 159930 | 281 | 3087 | mars 2020 | 1111.551472 | 2256.448528 | -24.911608 | 17.484525 |
| 2698384 | 28527 | 296576 | 96 | 2313 | petit fille | 795.049732 | 1613.950268 | -24.791964 | 17.400551 |
| 2000125 | 11578 | 86109 | 179 | 2586 | juin 2020 | 912.541515 | 1852.458485 | -24.282779 | 17.043173 |
| 1948390 | 233 | 9905 | 2 | 1724 | jade hallyday | 569.637126 | 1156.362874 | -23.783275 | 16.692590 |
| 283791 | 0 | 286064 | 0 | 1658 | amoureux 3 | 547.194876 | 1110.805124 | -23.392197 | 16.418107 |
| 451258 | 0 | 286031 | 0 | 1649 | avenir amoureux | 544.224578 | 1104.775422 | -23.328621 | 16.373486 |
| 104476 | 0 | 286130 | 0 | 1640 | 3 cliquer | 541.254280 | 1098.745720 | -23.264872 | 16.328743 |
| 3459583 | 436 | 25879 | 2 | 1635 | succulent recette | 540.264181 | 1096.735819 | -23.157538 | 16.253409 |
| 857431 | 6233 | 72652 | 114 | 2128 | compte instagram | 739.934205 | 1502.065795 | -23.010822 | 16.150434 |
| 2043436 | 2918 | 27488 | 9 | 1616 | laeticia hallyday | 536.303783 | 1088.696217 | -22.769603 | 15.981132 |
| 1601404 | 4105 | 52037 | 170 | 2293 | février 2020 | 812.871519 | 1650.128481 | -22.548270 | 15.825787 |
| 3522972 | 5064 | 1545219 | 69 | 1850 | série tv | 633.333514 | 1285.666486 | -22.424337 | 15.738802 |
| 1998626 | 14160 | 50831 | 207 | 2419 | juillet 2020 | 866.666914 | 1759.333086 | -22.407768 | 15.727173 |
fig = px.bar(graph_nonmedia2, x="res_nonmedia", y="bigramme", labels={"res_nonmedia":"Résiduel de Pearson","bigramme":"Bigramme (dans les posts Facebook <b>non-médias</b>)"}, orientation="h", title="Bigrammes les plus caractéristiques des posts Facebook <b>non-médias</b> {} en 2020".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="aqua", opacity=0.75, textfont_size=12)
fig
khi2_2["exp_inter_media"] = ((khi2_2.interactions_media + khi2_2.interactions_nonmedia) * khi2_2.interactions_media.sum()) / (khi2_2.interactions_media.sum() + khi2_2.interactions_nonmedia.sum())
khi2_2["exp_inter_nonmedia"] = ((khi2_2.interactions_media + khi2_2.interactions_nonmedia) * khi2_2.interactions_nonmedia.sum()) / (khi2_2.interactions_media.sum() + khi2_2.interactions_nonmedia.sum())
khi2_2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 1.328285 | 3.671715 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 47.552609 | 131.447391 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 1.328285 | 3.671715 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 2.656570 | 7.343430 |
| 4 | 0 | 1 | 0 | 1 | #6 ski | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 0.265657 | 0.734343 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 4023857 | 0 | 43 | 0 | 1 | samedi cavelescretet | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 11.423253 | 31.576747 |
| 4023858 | 0 | 30 | 0 | 3 | sea dahu | 0.990099 | 2.009901 | -0.995037 | 0.698379 | 7.969711 | 22.030289 |
| 4023859 | 0 | 0 | 0 | 1 | sen ira | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 0.000000 | 0.000000 |
| 4023860 | 0 | 0 | 0 | 1 | sonore des | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 0.000000 | 0.000000 |
| 4023861 | 0 | 0 | 0 | 2 | spontanes cie | 0.660066 | 1.339934 | -0.812445 | 0.570224 | 0.000000 | 0.000000 |
4023862 rows × 11 columns
khi2_2["res_inter_media"] = (khi2_2.interactions_media - khi2_2.exp_inter_media) / np.sqrt(khi2_2.exp_inter_media)
khi2_2["res_inter_nonmedia"] = (khi2_2.interactions_nonmedia - khi2_2.exp_inter_nonmedia) / np.sqrt(khi2_2.exp_inter_nonmedia)
khi2_2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 1.328285 | 3.671715 | -1.152513 | 0.693197 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 47.552609 | 131.447391 | 19.061839 | -11.465051 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 1.328285 | 3.671715 | 3.185835 | -1.916172 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 2.656570 | 7.343430 | 4.505451 | -2.709876 |
| 4 | 0 | 1 | 0 | 1 | #6 ski | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 0.265657 | 0.734343 | -0.515419 | 0.310007 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 4023857 | 0 | 43 | 0 | 1 | samedi cavelescretet | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 11.423253 | 31.576747 | -3.379830 | 2.032853 |
| 4023858 | 0 | 30 | 0 | 3 | sea dahu | 0.990099 | 2.009901 | -0.995037 | 0.698379 | 7.969711 | 22.030289 | -2.823068 | 1.697980 |
| 4023859 | 0 | 0 | 0 | 1 | sen ira | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 0.000000 | 0.000000 | NaN | NaN |
| 4023860 | 0 | 0 | 0 | 1 | sonore des | 0.330033 | 0.669967 | -0.574485 | 0.403210 | 0.000000 | 0.000000 | NaN | NaN |
| 4023861 | 0 | 0 | 0 | 2 | spontanes cie | 0.660066 | 1.339934 | -0.812445 | 0.570224 | 0.000000 | 0.000000 | NaN | NaN |
4023862 rows × 13 columns
graph_interactions_media2 = khi2_2.sort_values(by=["res_inter_media"],ascending=False).head(50)
graph_interactions_media2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 900227 | 814330 | 271088 | 4713 | 3257 | conseil fédéral | 2630.363787 | 5339.636213 | 40.607430 | -28.500835 | 288348.928578 | 797069.071422 | 979.514669 | -589.144919 |
| 949395 | 392132 | 6995 | 3530 | 133 | coronavirus suisse | 1208.911236 | 2454.088764 | 66.756651 | -46.853994 | 106030.895762 | 293096.104238 | 878.624519 | -528.462909 |
| 2480943 | 386653 | 20836 | 1613 | 265 | nouveau cas | 619.802157 | 1258.197843 | 39.894151 | -28.000211 | 108252.319896 | 299236.680104 | 846.158430 | -508.935655 |
| 3471275 | 243252 | 6291 | 3765 | 124 | suisse monde | 1283.498716 | 2605.501284 | 69.265470 | -48.614840 | 66292.853706 | 183250.146294 | 687.289418 | -413.381322 |
| 3368363 | 373285 | 114310 | 777 | 446 | soin intensif | 403.630478 | 819.369522 | 18.584329 | -13.043645 | 129533.042413 | 358061.957587 | 677.263747 | -407.351220 |
| 3705513 | 290967 | 62746 | 301 | 280 | universitaire genève | 191.749230 | 389.250770 | 7.889649 | -5.537449 | 93966.347134 | 259746.652866 | 642.660331 | -386.538436 |
| 2482377 | 276778 | 53705 | 919 | 505 | nouveau mesure | 469.967131 | 954.032869 | 20.713066 | -14.537725 | 87795.134191 | 242687.865809 | 637.803954 | -383.617490 |
| 95344 | 275062 | 60164 | 1282 | 423 | 24 heure | 562.706431 | 1142.293569 | 30.322516 | -21.282239 | 89055.145512 | 246170.854488 | 623.303319 | -374.895849 |
| 3790911 | 189631 | 1412 | 24 | 58 | vie coronavirus | 27.062714 | 54.937286 | -0.588736 | 0.413212 | 50751.917107 | 140291.082893 | 616.468108 | -370.784701 |
| 4010276 | 185290 | 408 | 2250 | 20 | évolution coronavirus | 749.175131 | 1520.824869 | 54.832537 | -38.484905 | 49331.980250 | 136366.019750 | 612.125619 | -368.172840 |
| 1795731 | 313013 | 105235 | 472 | 351 | hôpital universitaire | 271.617239 | 551.382761 | 12.158547 | -8.533629 | 111110.523945 | 307137.476055 | 605.709029 | -364.313479 |
| 3478120 | 181028 | 5939 | 1857 | 294 | suivre direct | 709.901193 | 1441.098807 | 43.052847 | -30.217181 | 49669.099029 | 137297.900971 | 589.408460 | -354.509238 |
| 2312231 | 225975 | 44929 | 350 | 199 | mise point | 181.188171 | 367.811829 | 12.541167 | -8.802176 | 71967.553650 | 198936.446350 | 574.081233 | -345.290430 |
| 3507473 | 167550 | 4267 | 71 | 115 | symptôme covid-19 | 61.386156 | 124.613844 | 1.227049 | -0.861220 | 45644.394935 | 126172.605065 | 570.597609 | -343.195148 |
| 191435 | 159582 | 930 | 2 | 45 | actuel maladie | 15.511556 | 31.488444 | -3.430660 | 2.407852 | 42641.142144 | 117870.857856 | 566.306910 | -340.614438 |
| 1185184 | 202352 | 30387 | 328 | 224 | début pandémie | 182.178270 | 369.821730 | 10.803736 | -7.582738 | 61828.752875 | 170910.247125 | 565.135948 | -339.910144 |
| 3342541 | 159429 | 1719 | 1786 | 14 | site app | 594.059576 | 1205.940424 | 48.903456 | -34.323504 | 42810.100019 | 118337.899981 | 563.632230 | -339.005709 |
| 2597559 | 156361 | 0 | 9 | 0 | pandémie revoir | 2.970298 | 6.029702 | 3.498613 | -2.455545 | 41538.399788 | 114822.600212 | 563.381389 | -338.854836 |
| 1244397 | 155893 | 0 | 1 | 0 | dérouter scientifique | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 41414.072295 | 114478.927705 | 562.537637 | -338.347348 |
| 980252 | 155893 | 0 | 1 | 0 | covid-19 dérouter | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 41414.072295 | 114478.927705 | 562.537637 | -338.347348 |
| 112220 | 155893 | 0 | 1 | 0 | 369 ici | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 41414.072295 | 114478.927705 | 562.537637 | -338.347348 |
| 3109439 | 155893 | 0 | 1 | 0 | revoir 369 | 0.330033 | 0.669967 | 1.166204 | -0.818515 | 41414.072295 | 114478.927705 | 562.537637 | -338.347348 |
| 1799839 | 155899 | 4 | 2 | 1 | ici connaissance | 0.990099 | 2.009901 | 1.014938 | -0.712347 | 41416.728866 | 114486.271134 | 562.536024 | -338.346378 |
| 3274708 | 155893 | 545 | 1 | 3 | scientifique début | 1.320132 | 2.679868 | -0.278626 | 0.195557 | 41558.855380 | 114879.144620 | 560.846686 | -337.330298 |
| 1133480 | 155914 | 821 | 2 | 1 | diversité symptôme | 0.990099 | 2.009901 | 1.014938 | -0.712347 | 41637.755520 | 115097.244480 | 560.031305 | -336.839874 |
| 892390 | 160488 | 8818 | 6 | 11 | connaissance actuel | 5.610563 | 11.389437 | 0.164412 | -0.115395 | 44977.330118 | 124328.669882 | 544.659730 | -327.594392 |
| 668659 | 173415 | 18480 | 688 | 181 | cas coronavirus | 286.798762 | 582.201238 | 23.690467 | -16.627452 | 50978.256901 | 140916.743099 | 542.274619 | -326.159828 |
| 2785155 | 299944 | 137392 | 1231 | 1275 | port masque | 827.062942 | 1678.937058 | 14.045733 | -9.858174 | 116181.385446 | 321154.614554 | 539.124273 | -324.265002 |
| 2528375 | 223949 | 64841 | 1182 | 620 | office fédéral | 594.719642 | 1207.280358 | 24.081822 | -16.902129 | 76719.095394 | 212070.904606 | 531.550210 | -319.709459 |
| 241871 | 227955 | 70029 | 973 | 225 | alain berset | 395.379651 | 802.620349 | 29.049277 | -20.388600 | 79161.546182 | 218822.453818 | 528.842915 | -318.081113 |
| 338814 | 134019 | 37 | 1464 | 2 | app évolution | 483.828521 | 982.171479 | 44.561144 | -31.275798 | 35612.919603 | 98443.080397 | 521.456571 | -313.638477 |
| 1178822 | 198935 | 48050 | 52 | 113 | durée vie | 54.455461 | 110.544539 | -0.332746 | 0.233542 | 65613.303008 | 181371.696992 | 520.481003 | -313.051706 |
| 1112001 | 129332 | 1473 | 1325 | 33 | direct site | 448.184946 | 909.815054 | 41.417069 | -29.069090 | 34749.268579 | 96055.731421 | 507.386629 | -305.175883 |
| 1596500 | 190643 | 49291 | 743 | 395 | fédéral santé | 375.577665 | 762.422335 | 18.959011 | -13.306620 | 63740.155248 | 176193.844752 | 502.648973 | -302.326343 |
| 3094039 | 118892 | 666 | 1448 | 5 | restezchezvous coronavirus | 479.538091 | 973.461909 | 44.225321 | -31.040097 | 31761.423896 | 87796.576104 | 488.900637 | -294.057185 |
| 1148401 | 184281 | 52439 | 1924 | 1136 | donald trump | 1009.901278 | 2050.098722 | 28.764289 | -20.188577 | 62886.333535 | 173833.666465 | 484.084825 | -291.160637 |
| 3069767 | 110710 | 0 | 6 | 0 | reportage soin | 1.980199 | 4.019801 | 2.856605 | -2.004944 | 29410.890443 | 81299.109557 | 474.058243 | -285.129987 |
| 2485760 | 117688 | 8583 | 256 | 30 | nouvo rts | 94.389466 | 191.610534 | 16.634429 | -11.675083 | 33544.779578 | 92726.220422 | 459.416574 | -276.323519 |
| 1899296 | 115809 | 7567 | 108 | 35 | intensif hôpital | 47.194733 | 95.805267 | 8.851043 | -6.212215 | 32775.702459 | 90600.297541 | 458.644597 | -275.859201 |
| 3642103 | 170928 | 52664 | 964 | 697 | transport public | 548.184975 | 1112.815025 | 17.759740 | -12.464897 | 59398.787968 | 164193.212032 | 457.614569 | -275.239674 |
| 3467748 | 113283 | 7600 | 520 | 88 | suisse compte | 200.660123 | 407.339877 | 22.543566 | -15.822485 | 32113.419469 | 88769.580531 | 452.949751 | -272.433944 |
| 668678 | 137850 | 26442 | 644 | 244 | cas covid-19 | 293.069391 | 594.930609 | 20.499158 | -14.387591 | 43645.325740 | 120646.674260 | 450.924241 | -271.215668 |
| 900128 | 213881 | 101114 | 1968 | 1461 | conseil etat | 1131.683491 | 2297.316509 | 24.860404 | -17.448587 | 83680.638019 | 231314.361981 | 450.090348 | -270.714110 |
| 236404 | 98912 | 0 | 7 | 0 | air etc | 2.310232 | 4.689768 | 3.085486 | -2.165587 | 26276.668734 | 72635.331266 | 448.087438 | -269.509427 |
| 3708054 | 98858 | 0 | 5 | 0 | up durée | 1.650165 | 3.349835 | 2.607712 | -1.830255 | 26262.323254 | 72595.676746 | 447.965107 | -269.435849 |
| 727587 | 105008 | 3793 | 36 | 12 | check up | 15.841589 | 32.158411 | 5.064737 | -3.554750 | 28903.751161 | 79897.248839 | 447.643001 | -269.242114 |
| 1231518 | 98385 | 0 | 16 | 0 | démêle vrai | 5.280530 | 10.719470 | 4.664817 | -3.274060 | 26136.667476 | 72248.332524 | 446.892146 | -268.790499 |
| 1745482 | 102067 | 2222 | 12 | 136 | heure air | 48.844898 | 99.155102 | -5.271907 | 3.700154 | 27705.106616 | 76583.893384 | 446.756136 | -268.708694 |
| 1327037 | 97148 | 0 | 6 | 0 | entendre durée | 1.980199 | 4.019801 | 2.856605 | -2.004944 | 25808.049722 | 71339.950278 | 444.073859 | -267.095395 |
| 1376023 | 97148 | 0 | 6 | 1 | etc entendre | 2.310232 | 4.689768 | 2.427568 | -1.703819 | 25808.049722 | 71339.950278 | 444.073859 | -267.095395 |
fig = px.bar(graph_interactions_media2, x="res_inter_media", y="bigramme", labels={"res_inter_media":"Résiduel de Pearson (<b>en fonction des interactions</b>)","bigramme":"Bigramme (dans les posts Facebook <b>médias</b>)"}, orientation="h", title="Bigrammes les plus caractéristiques des posts Facebook <b>médias</b> {} en 2020<br>(en fonction des interactions suscitées)".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="blue", opacity=0.75, textfont_size=12)
fig
graph_interactions_nonmedia2 = khi2_2.sort_values(by=["res_inter_nonmedia"],ascending=False).head(50)
graph_interactions_nonmedia2
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | bigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3594105 | 15577 | 4542299 | 420 | 20376 | timeline photo | 6863.368296 | 13932.631704 | -77.775767 | 54.587899 | 1.210832e+06 | 3.347044e+06 | -1086.221995 | 653.325764 |
| 3522972 | 5064 | 1545219 | 69 | 1850 | série tv | 633.333514 | 1285.666486 | -22.424337 | 15.738802 | 4.118436e+05 | 1.138439e+06 | -633.859490 | 381.245029 |
| 2710373 | 63129 | 1854100 | 1029 | 10642 | photo from | 3851.816281 | 7819.183719 | -45.483076 | 31.922868 | 5.093254e+05 | 1.407904e+06 | -625.213547 | 376.044787 |
| 3414200 | 0 | 947087 | 0 | 955 | souviens série | 315.181608 | 639.818392 | -17.753355 | 12.460415 | 2.516003e+05 | 6.954867e+05 | -501.597772 | 301.694082 |
| 321787 | 2562 | 961053 | 85 | 1757 | année 80 | 607.920966 | 1234.079034 | -21.208624 | 14.885539 | 2.559911e+05 | 7.076239e+05 | -500.891950 | 301.269554 |
| 791186 | 0 | 725245 | 0 | 774 | clique image | 255.445617 | 518.554383 | -15.982666 | 11.217635 | 1.926664e+05 | 5.325786e+05 | -438.937851 | 264.006260 |
| 1076444 | 3199 | 672725 | 29 | 1028 | dessin animer | 348.844984 | 708.155016 | -17.124713 | 12.019195 | 1.795640e+05 | 4.963600e+05 | -416.200622 | 250.330587 |
| 1975114 | 953 | 647673 | 21 | 1066 | johnny hallyday | 358.745977 | 728.254023 | -17.831861 | 12.515515 | 1.723121e+05 | 4.763139e+05 | -412.809074 | 248.290685 |
| 1076445 | 932 | 580058 | 22 | 1020 | dessin animé | 343.894488 | 698.105512 | -17.358050 | 12.182965 | 1.543441e+05 | 4.266459e+05 | -390.494186 | 234.869035 |
| 3674933 | 0 | 536864 | 0 | 436 | tv alffr | 143.894431 | 292.105569 | -11.995600 | 8.419263 | 1.426217e+05 | 3.942423e+05 | -377.652882 | 227.145426 |
| 3473957 | 108 | 536889 | 12 | 312 | suisse switzerland | 106.930724 | 217.069276 | -9.180272 | 6.443289 | 1.426570e+05 | 3.943400e+05 | -377.413716 | 227.001576 |
| 1249668 | 0 | 526121 | 0 | 446 | détail série | 147.194761 | 298.805239 | -12.132385 | 8.515267 | 1.397677e+05 | 3.863533e+05 | -373.855247 | 224.861277 |
| 259576 | 6990 | 548719 | 71 | 926 | aller loin | 329.042998 | 667.957002 | -14.225441 | 9.984305 | 1.476280e+05 | 4.080810e+05 | -366.031383 | 220.155488 |
| 3475246 | 0 | 483210 | 0 | 360 | suisseromande romandie | 118.811915 | 241.188085 | -10.900088 | 7.650364 | 1.283681e+05 | 3.548419e+05 | -358.284993 | 215.496296 |
| 1818865 | 0 | 454484 | 0 | 412 | image regarde | 135.973636 | 276.026364 | -11.660773 | 8.184260 | 1.207369e+05 | 3.337471e+05 | -347.472117 | 208.992717 |
| 249851 | 0 | 447036 | 0 | 686 | alffr propose | 226.402705 | 459.597295 | -15.046684 | 10.560704 | 1.187583e+05 | 3.282777e+05 | -344.613202 | 207.273176 |
| 2346415 | 0 | 439458 | 0 | 132 | montagne mountain | 43.564369 | 88.435631 | -6.600331 | 4.632525 | 1.167451e+05 | 3.227129e+05 | -341.679835 | 205.508856 |
| 3522433 | 10 | 425455 | 2 | 358 | série mythique | 118.811915 | 241.188085 | -10.716603 | 7.521582 | 1.130278e+05 | 3.124372e+05 | -336.166286 | 202.192642 |
| 1713036 | 0 | 399693 | 0 | 380 | générique détail | 125.412577 | 254.587423 | -11.198776 | 7.860001 | 1.061813e+05 | 2.935117e+05 | -325.854657 | 195.990547 |
| 1205541 | 628 | 392291 | 11 | 343 | découvrir série | 116.831717 | 237.168283 | -9.791190 | 6.872069 | 1.043817e+05 | 2.885373e+05 | -321.137782 | 193.153506 |
| 3272456 | 65 | 381425 | 3 | 239 | schweiz svizzera | 79.868010 | 162.131990 | -8.601203 | 6.036862 | 1.013455e+05 | 2.801445e+05 | -318.143905 | 191.352790 |
| 3594106 | 141 | 370029 | 5 | 322 | timeline photos | 107.920823 | 219.079177 | -9.907193 | 6.953488 | 9.833826e+04 | 2.718317e+05 | -313.139693 | 188.342926 |
| 249830 | 0 | 358995 | 0 | 841 | alffr découvrir | 277.557835 | 563.442165 | -16.660067 | 11.693077 | 9.536955e+04 | 2.636255e+05 | -308.819604 | 185.744539 |
| 3668066 | 0 | 344915 | 0 | 92 | trust nature | 30.363045 | 61.636955 | -5.510267 | 3.867450 | 9.162910e+04 | 2.532859e+05 | -302.702984 | 182.065599 |
| 3342498 | 0 | 335517 | 0 | 550 | site alffr | 181.518204 | 368.481796 | -13.472869 | 9.456102 | 8.913245e+04 | 2.463845e+05 | -298.550585 | 179.568072 |
| 3499876 | 0 | 331174 | 0 | 173 | svizzera schweiz | 57.095726 | 115.904274 | -7.556171 | 5.303394 | 8.797870e+04 | 2.431953e+05 | -296.612042 | 178.402103 |
| 3414159 | 0 | 330700 | 0 | 519 | souviens dessin | 171.287178 | 347.712822 | -13.087673 | 9.185747 | 8.785278e+04 | 2.428472e+05 | -296.399699 | 178.274387 |
| 504251 | 0 | 315819 | 0 | 4 | beauté vie | 1.320132 | 2.679868 | -1.148970 | 0.806419 | 8.389954e+04 | 2.319195e+05 | -289.654172 | 174.217180 |
| 2041590 | 1184 | 316529 | 27 | 166 | lac montagne | 63.696388 | 129.303612 | -4.597968 | 3.227141 | 8.440269e+04 | 2.333103e+05 | -286.445986 | 172.287565 |
| 3501474 | 0 | 304132 | 0 | 191 | swiss montagne | 63.036322 | 127.963678 | -7.939542 | 5.572467 | 8.079481e+04 | 2.233372e+05 | -284.244271 | 170.963308 |
| 2061713 | 0 | 304068 | 0 | 191 | lausanne mylausanne | 63.036322 | 127.963678 | -7.939542 | 5.572467 | 8.077780e+04 | 2.232902e+05 | -284.214362 | 170.945319 |
| 1808822 | 0 | 304065 | 0 | 190 | igerslausanne vaud | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 2063548 | 0 | 304065 | 0 | 190 | lausanneparcoeur lausanne | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 1808912 | 0 | 304065 | 0 | 190 | iglausann igerslausanne | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 2346292 | 0 | 304065 | 0 | 190 | montagne lacleman | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 2042499 | 0 | 304065 | 0 | 190 | lacleman leman | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 3504770 | 0 | 304065 | 0 | 190 | switzerland suisseromande | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 3136624 | 0 | 304065 | 0 | 190 | romandie switzerlandpicture | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 2396895 | 0 | 304065 | 0 | 190 | mylausanne iglausann | 62.706289 | 127.293711 | -7.918730 | 5.557860 | 8.077701e+04 | 2.232880e+05 | -284.212960 | 170.944475 |
| 3745749 | 7 | 304065 | 1 | 190 | vaud cantondevaud | 63.036322 | 127.963678 | -7.813590 | 5.484066 | 8.077887e+04 | 2.232931e+05 | -284.191602 | 170.931630 |
| 652739 | 0 | 301932 | 0 | 189 | cantondevaud suisse | 62.376255 | 126.623745 | -7.897864 | 5.543215 | 8.021036e+04 | 2.217216e+05 | -283.214336 | 170.343837 |
| 508103 | 378 | 298771 | 22 | 283 | bel soirée | 100.660095 | 204.339905 | -7.840176 | 5.502726 | 7.947104e+04 | 2.196780e+05 | -280.565206 | 168.750475 |
| 3032687 | 0 | 288145 | 0 | 204 | regarde générique | 67.326752 | 136.673248 | -8.205288 | 5.758984 | 7.654775e+04 | 2.115973e+05 | -276.672634 | 166.409225 |
| 104476 | 0 | 286130 | 0 | 1640 | 3 cliquer | 541.254280 | 1098.745720 | -23.264872 | 16.328743 | 7.601245e+04 | 2.101176e+05 | -275.703550 | 165.826354 |
| 283791 | 0 | 286064 | 0 | 1658 | amoureux 3 | 547.194876 | 1110.805124 | -23.392197 | 16.418107 | 7.599491e+04 | 2.100691e+05 | -275.671751 | 165.807227 |
| 451258 | 0 | 286031 | 0 | 1649 | avenir amoureux | 544.224578 | 1104.775422 | -23.328621 | 16.373486 | 7.598615e+04 | 2.100449e+05 | -275.655850 | 165.797663 |
| 1202766 | 83 | 286464 | 2 | 2110 | découvrir avenir | 697.029902 | 1414.970098 | -26.325570 | 18.476932 | 7.612323e+04 | 2.104238e+05 | -275.603551 | 165.766207 |
| 2398263 | 0 | 285180 | 0 | 152 | myswitzerland swiss | 50.165031 | 101.834969 | -7.082728 | 4.971101 | 7.576007e+04 | 2.094199e+05 | -275.245479 | 165.550839 |
| 3504974 | 0 | 285180 | 0 | 152 | switzerlandpicture svizzera | 50.165031 | 101.834969 | -7.082728 | 4.971101 | 7.576007e+04 | 2.094199e+05 | -275.245479 | 165.550839 |
| 3272360 | 0 | 285180 | 0 | 152 | schweiz myswitzerland | 50.165031 | 101.834969 | -7.082728 | 4.971101 | 7.576007e+04 | 2.094199e+05 | -275.245479 | 165.550839 |
fig = px.bar(graph_interactions_nonmedia2, x="res_inter_nonmedia", y="bigramme", labels={"res_inter_nonmedia":"Résiduel de Pearson (<b>en fonction des interactions</b>)","bigramme":"Bigramme (dans les posts Facebook <b>non-médias</b>)"}, orientation="h", title="Bigrammes les plus caractéristiques des posts Facebook <b>non-médias</b> {} en 2020<br>(en fonction des interactions suscitées)".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="cyan", opacity=0.75)
fig
media3 = pan.read_csv("suisse-trigrammes-media-nettoye.csv", low_memory=False, names=["trigramme","interactions"])
nonmedia3 = pan.read_csv("suisse-trigrammes-nonmedia-nettoye.csv", low_memory=False, names=["trigramme","interactions"])
media3
| trigramme | interactions | |
|---|---|---|
| 0 | donner enfant envie | 49596 |
| 1 | enfant envie intéresser | 49596 |
| 2 | envie intéresser biodiversité | 49596 |
| 3 | intéresser biodiversité falloir | 49596 |
| 4 | biodiversité falloir emmener | 49596 |
| ... | ... | ... |
| 4091708 | rtn complétez formulaire | 0 |
| 4091709 | complétez formulaire ici | 0 |
| 4091710 | formulaire ici jardinière | 0 |
| 4091711 | ici jardinière recruter | 0 |
| 4091712 | jardinière recruter rtn | 0 |
4091713 rows × 2 columns
nonmedia3
| trigramme | interactions | |
|---|---|---|
| 0 | falloir il faire | 107933 |
| 1 | il faire petit | 107933 |
| 2 | faire petit prince | 107933 |
| 3 | petit prince falloir | 107933 |
| 4 | prince falloir patient | 107933 |
| ... | ... | ... |
| 8334960 | competenze indipendentemente dal | 0 |
| 8334961 | indipendentemente dal tuo | 0 |
| 8334962 | dal tuo background | 0 |
| 8334963 | tuo background maggiori | 0 |
| 8334964 | background maggiori informazioni | 0 |
8334965 rows × 2 columns
media3_table = pan.pivot_table(media3,index=["trigramme"],values=["trigramme","interactions"],aggfunc=[len,np.sum])
nonmedia3_table = pan.pivot_table(nonmedia3,index=["trigramme"],values=["trigramme","interactions"],aggfunc=[len,np.sum])
media3_table
| len | sum | |
|---|---|---|
| interactions | interactions | |
| trigramme | ||
| #12h45rts chine cloître | 1 | 179 |
| #19h30rt crèches bernois | 1 | 5 |
| #19h30rt rtsinfo période | 1 | 10 |
| #coronaviru déclarer noir | 1 | 325 |
| #covid19 autorité soutenir | 1 | 199 |
| ... | ... | ... |
| 수원 이동국 덕분에챌린지 | 1 | 8 |
| 시즌 k리그 리드를 | 1 | 8 |
| 이동국 덕분에챌린지 thefansgame | 1 | 8 |
| 이동국의 시즌 k리그 | 1 | 8 |
| 전북 수원 이동국 | 1 | 8 |
2607587 rows × 2 columns
nonmedia3_table
| len | sum | |
|---|---|---|
| interactions | interactions | |
| trigramme | ||
| #111 disposition signaler | 1 | 5 |
| #6 ski orientation | 1 | 1 |
| #allezlausanne lswil dasilva | 1 | 105 |
| #allezxamax mafamille xama | 1 | 48 |
| #allezxamax pournoscouleur match | 1 | 65 |
| ... | ... | ... |
| samedi cavelescretet chateauleveque | 1 | 43 |
| sea dahu solo | 3 | 30 |
| sen ira collectif | 1 | 0 |
| sonore des femmes | 1 | 0 |
| spontanes cie sevenacts | 2 | 0 |
4343766 rows × 2 columns
media3_table["type"] = "media"
nonmedia3_table["type"] = "non-media"
media3_table
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| trigramme | |||
| #12h45rts chine cloître | 1 | 179 | media |
| #19h30rt crèches bernois | 1 | 5 | media |
| #19h30rt rtsinfo période | 1 | 10 | media |
| #coronaviru déclarer noir | 1 | 325 | media |
| #covid19 autorité soutenir | 1 | 199 | media |
| ... | ... | ... | ... |
| 수원 이동국 덕분에챌린지 | 1 | 8 | media |
| 시즌 k리그 리드를 | 1 | 8 | media |
| 이동국 덕분에챌린지 thefansgame | 1 | 8 | media |
| 이동국의 시즌 k리그 | 1 | 8 | media |
| 전북 수원 이동국 | 1 | 8 | media |
2607587 rows × 3 columns
nonmedia3_table
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| trigramme | |||
| #111 disposition signaler | 1 | 5 | non-media |
| #6 ski orientation | 1 | 1 | non-media |
| #allezlausanne lswil dasilva | 1 | 105 | non-media |
| #allezxamax mafamille xama | 1 | 48 | non-media |
| #allezxamax pournoscouleur match | 1 | 65 | non-media |
| ... | ... | ... | ... |
| samedi cavelescretet chateauleveque | 1 | 43 | non-media |
| sea dahu solo | 3 | 30 | non-media |
| sen ira collectif | 1 | 0 | non-media |
| sonore des femmes | 1 | 0 | non-media |
| spontanes cie sevenacts | 2 | 0 | non-media |
4343766 rows × 3 columns
tableau3 = pan.concat([media3_table,nonmedia3_table], names = ["trigramme","nb","interactions","type"], levels=0)
tableau3
| len | sum | type | |
|---|---|---|---|
| interactions | interactions | ||
| trigramme | |||
| #12h45rts chine cloître | 1 | 179 | media |
| #19h30rt crèches bernois | 1 | 5 | media |
| #19h30rt rtsinfo période | 1 | 10 | media |
| #coronaviru déclarer noir | 1 | 325 | media |
| #covid19 autorité soutenir | 1 | 199 | media |
| ... | ... | ... | ... |
| samedi cavelescretet chateauleveque | 1 | 43 | non-media |
| sea dahu solo | 3 | 30 | non-media |
| sen ira collectif | 1 | 0 | non-media |
| sonore des femmes | 1 | 0 | non-media |
| spontanes cie sevenacts | 2 | 0 | non-media |
6951353 rows × 3 columns
tableau3["trigramme"] = tableau3.index
tableau3.columns = ["nb","interactions","media","trigramme"]
tableau3.reset_index(drop=True, inplace=True)
tableau3
| nb | interactions | media | trigramme | |
|---|---|---|---|---|
| 0 | 1 | 179 | media | #12h45rts chine cloître |
| 1 | 1 | 5 | media | #19h30rt crèches bernois |
| 2 | 1 | 10 | media | #19h30rt rtsinfo période |
| 3 | 1 | 325 | media | #coronaviru déclarer noir |
| 4 | 1 | 199 | media | #covid19 autorité soutenir |
| ... | ... | ... | ... | ... |
| 6951348 | 1 | 43 | non-media | samedi cavelescretet chateauleveque |
| 6951349 | 3 | 30 | non-media | sea dahu solo |
| 6951350 | 1 | 0 | non-media | sen ira collectif |
| 6951351 | 1 | 0 | non-media | sonore des femmes |
| 6951352 | 2 | 0 | non-media | spontanes cie sevenacts |
6951353 rows × 4 columns
khi2_3 = pan.pivot_table(tableau3,index=["trigramme"],columns=["media"],values=["trigramme","interactions"],aggfunc=[len,np.sum],fill_value=0)
khi2_3
| len | sum | |||||||
|---|---|---|---|---|---|---|---|---|
| interactions | nb | interactions | nb | |||||
| media | media | non-media | media | non-media | media | non-media | media | non-media |
| trigramme | ||||||||
| #111 disposition signaler | 0 | 1 | 0 | 1 | 0 | 5 | 0 | 1 |
| #12h45rts chine cloître | 1 | 0 | 1 | 0 | 179 | 0 | 1 | 0 |
| #19h30rt crèches bernois | 1 | 0 | 1 | 0 | 5 | 0 | 1 | 0 |
| #19h30rt rtsinfo période | 1 | 0 | 1 | 0 | 10 | 0 | 1 | 0 |
| #6 ski orientation | 0 | 1 | 0 | 1 | 0 | 1 | 0 | 1 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... |
| samedi cavelescretet chateauleveque | 0 | 1 | 0 | 1 | 0 | 43 | 0 | 1 |
| sea dahu solo | 0 | 1 | 0 | 1 | 0 | 30 | 0 | 3 |
| sen ira collectif | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 1 |
| sonore des femmes | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 1 |
| spontanes cie sevenacts | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 2 |
6749558 rows × 8 columns
khi2_3["trigramme"] = khi2_3.index
khi2_3.columns = khi2_3.columns.get_level_values(0)
khi2_3.reset_index(drop=True, inplace=True)
khi2_3.columns = ["a","b","c","d","interactions_media","interactions_nonmedia","obs_media","obs_nonmedia","trigramme"]
khi2_3 = khi2_3.drop(columns=["a","b","c","d"])
khi2_3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | |
|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition signaler |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine cloître |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches bernois |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo période |
| 4 | 0 | 1 | 0 | 1 | #6 ski orientation |
| ... | ... | ... | ... | ... | ... |
| 6749553 | 0 | 43 | 0 | 1 | samedi cavelescretet chateauleveque |
| 6749554 | 0 | 30 | 0 | 3 | sea dahu solo |
| 6749555 | 0 | 0 | 0 | 1 | sen ira collectif |
| 6749556 | 0 | 0 | 0 | 1 | sonore des femmes |
| 6749557 | 0 | 0 | 0 | 2 | spontanes cie sevenacts |
6749558 rows × 5 columns
khi2_3.obs_media.sum(), khi2_3.obs_nonmedia.sum()
(4091713, 8334965)
print("Nb de lignes fichier media3 = ", media3.shape[0])
print("Somme observée média khi2_3 = ", khi2_3.obs_media.sum())
print("Nb de lignes fichier nonmedia3 = ", nonmedia3.shape[0])
print("Somme observée nonmédia khi2_3 = ", khi2_3.obs_nonmedia.sum())
Nb de lignes fichier media3 = 4091713 Somme observée média khi2_3 = 4091713 Nb de lignes fichier nonmedia3 = 8334965 Somme observée nonmédia khi2_3 = 8334965
khi2_3["exp_media"] = ((khi2_3.obs_media + khi2_3.obs_nonmedia) * khi2_3.obs_media.sum()) / (khi2_3.obs_media.sum() + khi2_3.obs_nonmedia.sum())
khi2_3["exp_nonmedia"] = ((khi2_3.obs_media + khi2_3.obs_nonmedia) * khi2_3.obs_nonmedia.sum()) / (khi2_3.obs_media.sum() + khi2_3.obs_nonmedia.sum())
khi2_3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | |
|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition signaler | 0.329268 | 0.670732 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine cloître | 0.329268 | 0.670732 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches bernois | 0.329268 | 0.670732 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo période | 0.329268 | 0.670732 |
| 4 | 0 | 1 | 0 | 1 | #6 ski orientation | 0.329268 | 0.670732 |
| ... | ... | ... | ... | ... | ... | ... | ... |
| 6749553 | 0 | 43 | 0 | 1 | samedi cavelescretet chateauleveque | 0.329268 | 0.670732 |
| 6749554 | 0 | 30 | 0 | 3 | sea dahu solo | 0.987805 | 2.012195 |
| 6749555 | 0 | 0 | 0 | 1 | sen ira collectif | 0.329268 | 0.670732 |
| 6749556 | 0 | 0 | 0 | 1 | sonore des femmes | 0.329268 | 0.670732 |
| 6749557 | 0 | 0 | 0 | 2 | spontanes cie sevenacts | 0.658537 | 1.341463 |
6749558 rows × 7 columns
khi2_3["res_media"] = (khi2_3.obs_media - khi2_3.exp_media) / np.sqrt(khi2_3.exp_media)
khi2_3["res_nonmedia"] = (khi2_3.obs_nonmedia - khi2_3.exp_nonmedia) / np.sqrt(khi2_3.exp_nonmedia)
khi2_3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition signaler | 0.329268 | 0.670732 | -0.573819 | 0.402046 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine cloître | 0.329268 | 0.670732 | 1.168890 | -0.818982 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches bernois | 0.329268 | 0.670732 | 1.168890 | -0.818982 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo période | 0.329268 | 0.670732 | 1.168890 | -0.818982 |
| 4 | 0 | 1 | 0 | 1 | #6 ski orientation | 0.329268 | 0.670732 | -0.573819 | 0.402046 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 6749553 | 0 | 43 | 0 | 1 | samedi cavelescretet chateauleveque | 0.329268 | 0.670732 | -0.573819 | 0.402046 |
| 6749554 | 0 | 30 | 0 | 3 | sea dahu solo | 0.987805 | 2.012195 | -0.993884 | 0.696364 |
| 6749555 | 0 | 0 | 0 | 1 | sen ira collectif | 0.329268 | 0.670732 | -0.573819 | 0.402046 |
| 6749556 | 0 | 0 | 0 | 1 | sonore des femmes | 0.329268 | 0.670732 | -0.573819 | 0.402046 |
| 6749557 | 0 | 0 | 0 | 2 | spontanes cie sevenacts | 0.658537 | 1.341463 | -0.811503 | 0.568579 |
6749558 rows × 9 columns
graph_media3 = khi2_3.sort_values(by=["res_media"],ascending=False).head(50)
graph_media3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 1568440 | 206573 | 272 | 2597 | 7 | coronavirus suisse monde | 857.415043 | 1746.584957 | 59.408706 | -41.624668 |
| 6724272 | 165207 | 198 | 2086 | 4 | évolution coronavirus suisse | 688.171060 | 1401.828940 | 53.285105 | -37.334171 |
| 5597189 | 134019 | 37 | 1464 | 2 | site app évolution | 482.707547 | 983.292453 | 44.663877 | -31.293714 |
| 5849788 | 126391 | 38 | 1301 | 3 | suivre direct site | 429.366058 | 874.633942 | 42.064940 | -29.472771 |
| 1849265 | 126366 | 37 | 1298 | 2 | direct site app | 428.048985 | 871.951015 | 42.048263 | -29.461086 |
| 576934 | 125325 | 37 | 1289 | 2 | app évolution coronavirus | 425.085569 | 865.914431 | 41.901787 | -29.358458 |
| 5825240 | 18561 | 0 | 654 | 0 | suisse monde coronavirus | 215.341566 | 438.658434 | 29.892521 | -20.944174 |
| 1378666 | 20335 | 0 | 536 | 0 | commune montreux mymontreuxch | 176.487889 | 359.512111 | 27.061762 | -18.960805 |
| 4072431 | 20335 | 0 | 536 | 0 | news commune montreux | 176.487889 | 359.512111 | 27.061762 | -18.960805 |
| 1631147 | 16517 | 0 | 466 | 0 | covid-19 suisse monde | 153.439098 | 312.560902 | 25.232869 | -17.679392 |
| 6724299 | 12835 | 0 | 422 | 0 | évolution covid-19 suisse | 138.951286 | 283.048714 | 24.012087 | -16.824052 |
| 3462846 | 38444 | 181 | 425 | 6 | lier coronavirus suisse | 141.914702 | 289.085298 | 23.763129 | -16.649619 |
| 5203865 | 7420 | 0 | 373 | 0 | retrouver ici principal | 122.817132 | 250.182868 | 22.575017 | -15.817170 |
| 2481740 | 6473 | 0 | 353 | 0 | fin direct retrouver | 116.231763 | 236.768237 | 21.961451 | -15.387275 |
| 1849030 | 7033 | 0 | 348 | 0 | direct retrouver ici | 114.585420 | 233.414580 | 21.805362 | -15.277911 |
| 2986724 | 12655 | 0 | 341 | 0 | ici info principal | 112.280541 | 228.719459 | 21.584941 | -15.123474 |
| 5203815 | 11724 | 65 | 336 | 2 | retrouver ici info | 111.292736 | 226.707264 | 21.300201 | -14.923971 |
| 323173 | 26922 | 5 | 332 | 1 | actualité lier coronavirus | 109.646394 | 223.353606 | 21.234743 | -14.878108 |
| 3692880 | 39547 | 9 | 319 | 2 | mars suivre direct | 105.695172 | 215.304828 | 20.747850 | -14.536967 |
| 2963138 | 7518 | 355 | 317 | 3 | humour jérémy vaillot | 105.365904 | 214.634096 | 20.617480 | -14.445623 |
| 5010542 | 6754 | 498 | 349 | 22 | radio lac matin | 122.158595 | 248.841405 | 20.523920 | -14.380070 |
| 2786134 | 1278 | 0 | 306 | 0 | grand étape pandémie | 100.756146 | 205.243854 | 20.447226 | -14.326334 |
| 5825339 | 22695 | 5 | 303 | 1 | suisse monde site | 100.097609 | 203.902391 | 20.280344 | -14.209409 |
| 3897037 | 22124 | 5 | 299 | 1 | monde site app | 98.780535 | 201.219465 | 20.145155 | -14.114689 |
| 3279384 | 2717 | 0 | 294 | 0 | jour choix midi | 96.804924 | 197.195076 | 20.042290 | -14.042616 |
| 3761943 | 2717 | 4 | 294 | 1 | menu jour choix | 97.134193 | 197.865807 | 19.974882 | -13.995387 |
| 4751287 | 4852 | 4 | 276 | 1 | principal info jour | 91.207361 | 185.792639 | 19.349499 | -13.557213 |
| 2522551 | 1424 | 0 | 269 | 0 | fois jour point | 88.573213 | 180.426787 | 19.171223 | -13.432304 |
| 3287772 | 1424 | 0 | 269 | 0 | jour point situation | 88.573213 | 180.426787 | 19.171223 | -13.432304 |
| 4211409 | 190527 | 48776 | 738 | 389 | office fédéral santé | 371.085543 | 755.914457 | 19.047054 | -13.345305 |
| 3889057 | 4281 | 0 | 263 | 0 | monde coronavirus nouveau | 86.597602 | 176.402398 | 18.956212 | -13.281656 |
| 778176 | 28216 | 28 | 262 | 1 | avril suivre direct | 86.597602 | 176.402398 | 18.848752 | -13.206365 |
| 3412481 | 13166 | 30193 | 548 | 218 | lausanne hockey club | 252.219632 | 513.780368 | 18.624297 | -13.049101 |
| 2988776 | 4378 | 0 | 252 | 0 | ici principal info | 82.975649 | 169.024351 | 18.555555 | -13.000937 |
| 2650247 | 185113 | 48437 | 709 | 380 | fédéral santé public | 358.573342 | 730.426658 | 18.505812 | -12.966084 |
| 3292806 | 4219 | 0 | 249 | 0 | jour évolution covid-19 | 81.987844 | 167.012156 | 18.444774 | -12.923318 |
| 3270642 | 2249 | 4 | 248 | 1 | jouer ici concours | 81.987844 | 167.012156 | 18.334335 | -12.845939 |
| 1096789 | 68249 | 1407 | 268 | 12 | cas 24 heure | 92.195166 | 187.804834 | 18.309511 | -12.828546 |
| 3086667 | 4224 | 0 | 243 | 0 | info jour évolution | 80.012233 | 162.987767 | 18.221193 | -12.766666 |
| 4120436 | 65884 | 1360 | 258 | 10 | nouveau cas 24 | 88.243945 | 179.756055 | 18.071026 | -12.661452 |
| 4619272 | 1193 | 0 | 234 | 0 | point situation travers | 77.048817 | 156.951183 | 17.880580 | -12.528016 |
| 5608033 | 1193 | 0 | 234 | 0 | situation travers carte | 77.048817 | 156.951183 | 17.880580 | -12.528016 |
| 5010507 | 4275 | 18 | 215 | 3 | radio lac genève | 71.780522 | 146.219478 | 16.904362 | -11.844029 |
| 3605996 | 15944 | 63 | 211 | 1 | mai suivre direct | 69.804911 | 142.195089 | 16.899607 | -11.840698 |
| 6323170 | 5586 | 354 | 208 | 1 | version ligne ici | 68.817106 | 140.182894 | 16.777902 | -11.755425 |
| 1245579 | 1314 | 0 | 206 | 0 | chronique air temps | 67.829301 | 138.170699 | 16.776729 | -11.754603 |
| 2713878 | 3980 | 18 | 209 | 3 | genève 918 lausanne | 69.804911 | 142.195089 | 16.660227 | -11.672977 |
| 3378019 | 3980 | 18 | 209 | 3 | lac genève 918 | 69.804911 | 142.195089 | 16.660227 | -11.672977 |
| 248927 | 3980 | 18 | 209 | 3 | 918 lausanne 956 | 69.804911 | 142.195089 | 16.660227 | -11.672977 |
| 5939571 | 2078 | 4 | 200 | 1 | tarder jouer ici | 66.182958 | 134.817042 | 16.448956 | -11.524949 |
fig = px.bar(graph_media3, x="res_media", y="trigramme", labels={"res_media":"Résiduel de Pearson","trigramme":"Trigramme (dans les posts Facebook <b>médias</b>)"}, orientation="h", title="Trigrammes les plus caractéristiques des posts Facebook <b>médias</b> {} en 2020".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="DarkOliveGreen", opacity=0.75, textfont_size=12)
fig
graph_nonmedia3 = khi2_3.sort_values(by=["res_nonmedia"],ascending=False).head(50)
graph_nonmedia3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|
| 138662 | 0 | 5615 | 0 | 5280 | 2020 savoir journée | 1738.537414 | 3541.462586 | -41.695772 | 29.214114 |
| 138273 | 0 | 2604 | 0 | 2857 | 2020 réserve surprise | 940.719961 | 1916.280039 | -30.671158 | 21.489726 |
| 6732580 | 0 | 2511 | 0 | 2777 | être capricorne vierge | 914.378485 | 1862.621515 | -30.238692 | 21.186718 |
| 1080300 | 0 | 2511 | 0 | 2777 | capricorne vierge scorpion | 914.378485 | 1862.621515 | -30.238692 | 21.186718 |
| 6367242 | 0 | 2417 | 0 | 2717 | vierge scorpion journée | 894.622378 | 1822.377622 | -29.910239 | 20.956588 |
| 678679 | 0 | 2268 | 0 | 2597 | astre être capricorne | 855.110164 | 1741.889836 | -29.242267 | 20.488574 |
| 4880452 | 0 | 2268 | 0 | 2597 | prédire astre être | 855.110164 | 1741.889836 | -29.242267 | 20.488574 |
| 136895 | 0 | 2200 | 0 | 2557 | 2020 prédire astre | 841.939426 | 1715.060574 | -29.016192 | 20.330175 |
| 465606 | 0 | 2159 | 0 | 2517 | amour argent santé | 828.768688 | 1688.231312 | -28.788343 | 20.170532 |
| 5444549 | 0 | 2159 | 0 | 2517 | santé découvrir horoscope | 828.768688 | 1688.231312 | -28.788343 | 20.170532 |
| 620195 | 0 | 2159 | 0 | 2517 | argent santé découvrir | 828.768688 | 1688.231312 | -28.788343 | 20.170532 |
| 5468058 | 0 | 2095 | 0 | 2440 | savoir journée amour | 803.415017 | 1636.584983 | -28.344577 | 19.859608 |
| 3297834 | 0 | 2079 | 0 | 2420 | journée amour argent | 796.829648 | 1623.170352 | -28.228171 | 19.778048 |
| 2945607 | 0 | 3458 | 0 | 2192 | horoscope jour gratuit | 721.756442 | 1470.243558 | -26.865525 | 18.823311 |
| 2007844 | 0 | 1057 | 0 | 1758 | découvrir signe horoscope | 578.853935 | 1179.146065 | -24.059384 | 16.857190 |
| 755816 | 0 | 285940 | 0 | 1635 | avenir amoureux 3 | 538.353915 | 1096.646085 | -23.202455 | 16.256784 |
| 467945 | 0 | 285940 | 0 | 1635 | amoureux 3 cliquer | 538.353915 | 1096.646085 | -23.202455 | 16.256784 |
| 1998481 | 0 | 285940 | 0 | 1635 | découvrir avenir amoureux | 538.353915 | 1096.646085 | -23.202455 | 16.256784 |
| 5468066 | 0 | 1808 | 0 | 1460 | savoir journée horoscope | 480.731937 | 979.268063 | -21.925600 | 15.362156 |
| 2008257 | 0 | 22601 | 0 | 1433 | découvrir succulent recette | 471.841688 | 961.158312 | -21.721917 | 15.219446 |
| 2006796 | 20 | 17303 | 1 | 1222 | découvrir recette facile | 402.695314 | 820.304686 | -20.017437 | 14.025203 |
| 5011124 | 117 | 16269 | 2 | 1144 | radio one fm | 377.341643 | 768.658357 | -19.322325 | 13.538173 |
| 6411919 | 0 | 31929 | 0 | 1130 | visible plate forme | 372.073348 | 757.926652 | -19.289203 | 13.514966 |
| 4590935 | 0 | 31929 | 0 | 1130 | plate forme petalert | 372.073348 | 757.926652 | -19.289203 | 13.514966 |
| 1302601 | 0 | 31929 | 0 | 1130 | clos visible plate | 372.073348 | 757.926652 | -19.289203 | 13.514966 |
| 3364234 | 40 | 1512 | 1 | 1134 | koh lanta terre | 373.719690 | 761.280310 | -19.280103 | 13.508591 |
| 570509 | 12 | 1486 | 1 | 1121 | août 2020 savoir | 369.439201 | 752.560799 | -19.168774 | 13.430588 |
| 35932 | 0 | 2680 | 0 | 1103 | 12 prénom porter | 363.183100 | 739.816900 | -19.057363 | 13.352528 |
| 3310539 | 0 | 1282 | 0 | 1040 | juillet 2020 savoir | 342.439188 | 697.560812 | -18.505112 | 12.965594 |
| 4885080 | 0 | 2946 | 0 | 1016 | prénom porter femme | 334.536745 | 681.463255 | -18.290346 | 12.815118 |
| 5576090 | 0 | 324 | 0 | 1015 | signe horoscope incompatible | 334.207476 | 680.792524 | -18.281342 | 12.808810 |
| 5052883 | 0 | 13435 | 0 | 1013 | recette facile découvrir | 333.548940 | 679.451060 | -18.263322 | 12.796184 |
| 2560085 | 0 | 27536 | 0 | 1008 | forme petalert france | 331.902597 | 676.097403 | -18.218194 | 12.764565 |
| 34334 | 1325 | 10434 | 7 | 1029 | 12 coup midi | 341.122114 | 694.877886 | -18.090488 | 12.675088 |
| 2361509 | 0 | 13155 | 0 | 993 | facile découvrir recette | 326.963571 | 666.036429 | -18.082134 | 12.669235 |
| 2146664 | 0 | 2394 | 0 | 942 | enceint 11 an | 310.170880 | 631.829120 | -17.611669 | 12.339603 |
| 2819253 | 0 | 1091 | 0 | 920 | grâce horoscope jour | 302.926974 | 617.073026 | -17.404797 | 12.194659 |
| 411004 | 0 | 97301 | 0 | 917 | alert pet alert | 301.939168 | 615.060832 | -17.376397 | 12.174760 |
| 4502779 | 0 | 18855 | 0 | 915 | petit fille tuer | 301.280631 | 613.719369 | -17.357437 | 12.161476 |
| 3636615 | 0 | 18855 | 0 | 915 | maltraiter propre parent | 301.280631 | 613.719369 | -17.357437 | 12.161476 |
| 6159193 | 0 | 18855 | 0 | 915 | tuer maltraiter propre | 301.280631 | 613.719369 | -17.357437 | 12.161476 |
| 2471403 | 0 | 18855 | 0 | 915 | fille tuer maltraiter | 301.280631 | 613.719369 | -17.357437 | 12.161476 |
| 3673276 | 0 | 11506 | 0 | 870 | marecettech propose découvrir | 286.463551 | 583.536449 | -16.925234 | 11.858653 |
| 4497080 | 0 | 90169 | 0 | 866 | pet alert pet | 285.146477 | 580.853523 | -16.886281 | 11.831361 |
| 4870637 | 0 | 42900 | 0 | 846 | provoquer trouble santé | 278.561108 | 567.438892 | -16.690150 | 11.693942 |
| 6710478 | 0 | 583 | 0 | 835 | étude faire astrologue | 274.939156 | 560.060844 | -16.581289 | 11.617669 |
| 5600733 | 0 | 263 | 0 | 825 | site rencontre gratuit | 271.646471 | 553.353529 | -16.481701 | 11.547892 |
| 1128688 | 0 | 67069 | 0 | 818 | centre accueil universel | 269.341592 | 548.658408 | -16.411630 | 11.498797 |
| 5599790 | 0 | 10462 | 0 | 810 | site marecettech propose | 266.707444 | 543.292556 | -16.331180 | 11.442430 |
| 6472205 | 0 | 6814 | 0 | 802 | vouloir célibataire texte | 264.073297 | 537.926703 | -16.250332 | 11.385784 |
fig = px.bar(graph_nonmedia3, x="res_nonmedia", y="trigramme", labels={"res_nonmedia":"Résiduel de Pearson","trigramme":"Trigramme (dans les posts Facebook <b>non-médias</b>)"}, orientation="h", title="Trigrammes les plus caractéristiques des posts Facebook <b>non-médias</b> {} en 2020".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="Olive", opacity=0.75, textfont_size=12)
fig
khi2_3["exp_inter_media"] = ((khi2_3.interactions_media + khi2_3.interactions_nonmedia) * khi2_3.interactions_media.sum()) / (khi2_3.interactions_media.sum() + khi2_3.interactions_nonmedia.sum())
khi2_3["exp_inter_nonmedia"] = ((khi2_3.interactions_media + khi2_3.interactions_nonmedia) * khi2_3.interactions_nonmedia.sum()) / (khi2_3.interactions_media.sum() + khi2_3.interactions_nonmedia.sum())
khi2_3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition signaler | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 1.321568 | 3.678432 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine cloître | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 47.312136 | 131.687864 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches bernois | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 1.321568 | 3.678432 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo période | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 2.643136 | 7.356864 |
| 4 | 0 | 1 | 0 | 1 | #6 ski orientation | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 0.264314 | 0.735686 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 6749553 | 0 | 43 | 0 | 1 | samedi cavelescretet chateauleveque | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 11.365485 | 31.634515 |
| 6749554 | 0 | 30 | 0 | 3 | sea dahu solo | 0.987805 | 2.012195 | -0.993884 | 0.696364 | 7.929408 | 22.070592 |
| 6749555 | 0 | 0 | 0 | 1 | sen ira collectif | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 0.000000 | 0.000000 |
| 6749556 | 0 | 0 | 0 | 1 | sonore des femmes | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 0.000000 | 0.000000 |
| 6749557 | 0 | 0 | 0 | 2 | spontanes cie sevenacts | 0.658537 | 1.341463 | -0.811503 | 0.568579 | 0.000000 | 0.000000 |
6749558 rows × 11 columns
khi2_3["res_inter_media"] = (khi2_3.interactions_media - khi2_3.exp_inter_media) / np.sqrt(khi2_3.exp_inter_media)
khi2_3["res_inter_nonmedia"] = (khi2_3.interactions_nonmedia - khi2_3.exp_inter_nonmedia) / np.sqrt(khi2_3.exp_inter_nonmedia)
khi2_3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 5 | 0 | 1 | #111 disposition signaler | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 1.321568 | 3.678432 | -1.149595 | 0.689062 |
| 1 | 179 | 0 | 1 | 0 | #12h45rts chine cloître | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 47.312136 | 131.687864 | 19.145181 | -11.475533 |
| 2 | 5 | 0 | 1 | 0 | #19h30rt crèches bernois | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 1.321568 | 3.678432 | 3.199764 | -1.917924 |
| 3 | 10 | 0 | 1 | 0 | #19h30rt rtsinfo période | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 2.643136 | 7.356864 | 4.525150 | -2.712354 |
| 4 | 0 | 1 | 0 | 1 | #6 ski orientation | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 0.264314 | 0.735686 | -0.514114 | 0.308158 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 6749553 | 0 | 43 | 0 | 1 | samedi cavelescretet chateauleveque | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 11.365485 | 31.634515 | -3.371274 | 2.020726 |
| 6749554 | 0 | 30 | 0 | 3 | sea dahu solo | 0.987805 | 2.012195 | -0.993884 | 0.696364 | 7.929408 | 22.070592 | -2.815920 | 1.687850 |
| 6749555 | 0 | 0 | 0 | 1 | sen ira collectif | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 0.000000 | 0.000000 | NaN | NaN |
| 6749556 | 0 | 0 | 0 | 1 | sonore des femmes | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 0.000000 | 0.000000 | NaN | NaN |
| 6749557 | 0 | 0 | 0 | 2 | spontanes cie sevenacts | 0.658537 | 1.341463 | -0.811503 | 0.568579 | 0.000000 | 0.000000 | NaN | NaN |
6749558 rows × 13 columns
graph_interactions_media3 = khi2_3.sort_values(by=["res_inter_media"],ascending=False).head(50)
graph_interactions_media3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1568440 | 206573 | 272 | 2597 | 7 | coronavirus suisse monde | 857.415043 | 1746.584957 | 59.408706 | -41.624668 | 54671.948378 | 152173.051622 | 649.648597 | -389.396376 |
| 2977509 | 290704 | 62285 | 300 | 266 | hôpital universitaire genève | 186.365943 | 379.634057 | 8.323869 | -5.832113 | 93299.796398 | 259689.203602 | 646.273054 | -387.373091 |
| 1956122 | 188166 | 1052 | 13 | 22 | durée vie coronavirus | 11.524396 | 23.475604 | 0.434671 | -0.304552 | 50012.892398 | 139205.107602 | 617.759841 | -370.282403 |
| 6724272 | 165207 | 198 | 2086 | 4 | évolution coronavirus suisse | 688.171060 | 1401.828940 | 53.285105 | -37.334171 | 43718.792436 | 121686.207564 | 581.031992 | -348.267899 |
| 1463794 | 159582 | 0 | 2 | 0 | connaissance actuel maladie | 0.658537 | 1.341463 | 1.653060 | -1.158215 | 42179.694293 | 117402.305707 | 571.643030 | -342.640199 |
| 2071319 | 155893 | 0 | 1 | 0 | dérouter scientifique début | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 5892160 | 155893 | 0 | 1 | 0 | symptôme covid-19 dérouter | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 5483905 | 155893 | 0 | 1 | 0 | scientifique début pandémie | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 4322927 | 155893 | 0 | 1 | 0 | pandémie revoir 369 | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 202656 | 155893 | 0 | 1 | 0 | 369 ici connaissance | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 1623665 | 155893 | 0 | 1 | 0 | covid-19 dérouter scientifique | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 1884105 | 155893 | 0 | 1 | 0 | diversité symptôme covid-19 | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 2985005 | 155893 | 0 | 1 | 0 | ici connaissance actuel | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 1967280 | 155893 | 0 | 1 | 0 | début pandémie revoir | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 5217274 | 155893 | 0 | 1 | 0 | revoir 369 ici | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 41204.641391 | 114688.358609 | 564.997164 | -338.656697 |
| 5597189 | 134019 | 37 | 1464 | 2 | site app évolution | 482.707547 | 983.292453 | 44.663877 | -31.293714 | 35432.825119 | 98623.174881 | 523.736843 | -313.925451 |
| 5849788 | 126391 | 38 | 1301 | 3 | suivre direct site | 429.366058 | 874.633942 | 42.064940 | -29.472771 | 33416.905226 | 93012.094774 | 508.602915 | -304.854244 |
| 1849265 | 126366 | 37 | 1298 | 2 | direct site app | 428.048985 | 871.951015 | 42.048263 | -29.461086 | 33410.033072 | 92992.966928 | 508.556044 | -304.826150 |
| 576934 | 125325 | 37 | 1289 | 2 | app évolution coronavirus | 425.085569 | 865.914431 | 41.901787 | -29.358458 | 33134.882605 | 92227.117395 | 506.455918 | -303.567344 |
| 4211409 | 190527 | 48776 | 738 | 389 | office fédéral santé | 371.085543 | 755.914457 | 19.047054 | -13.345305 | 63251.039487 | 176051.960513 | 506.072280 | -303.337393 |
| 2650247 | 185113 | 48437 | 709 | 380 | fédéral santé public | 358.573342 | 730.426658 | 18.505812 | -12.966084 | 61730.443296 | 171819.556704 | 496.596972 | -297.657938 |
| 5644634 | 115484 | 7405 | 107 | 33 | soin intensif hôpital | 46.097583 | 93.902417 | 8.970062 | -6.284868 | 32481.235051 | 90407.764949 | 460.549476 | -276.051234 |
| 3138184 | 100303 | 750 | 15 | 6 | intensif hôpital universitaire | 6.914637 | 14.085363 | 3.074785 | -2.154346 | 26709.683093 | 74343.316907 | 450.302139 | -269.909028 |
| 1196388 | 98858 | 0 | 5 | 0 | check up durée | 1.646342 | 3.353658 | 2.613718 | -1.831299 | 26129.514722 | 72728.485278 | 449.923700 | -269.682193 |
| 6213791 | 98858 | 0 | 5 | 0 | up durée vie | 1.646342 | 3.353658 | 2.613718 | -1.831299 | 26129.514722 | 72728.485278 | 449.923700 | -269.682193 |
| 2050986 | 98385 | 0 | 16 | 0 | démêle vrai faux | 5.268295 | 10.731705 | 4.675560 | -3.275928 | 26004.494385 | 72380.505615 | 448.846048 | -269.036253 |
| 2197425 | 97148 | 0 | 6 | 0 | entendre durée vie | 1.975611 | 4.024389 | 2.863184 | -2.006088 | 25677.538451 | 71470.461549 | 446.015439 | -267.339600 |
| 395968 | 97148 | 0 | 6 | 0 | air etc entendre | 1.975611 | 4.024389 | 2.863184 | -2.006088 | 25677.538451 | 71470.461549 | 446.015439 | -267.339600 |
| 3287680 | 97148 | 0 | 6 | 0 | jour plastique heure | 1.975611 | 4.024389 | 2.863184 | -2.006088 | 25677.538451 | 71470.461549 | 446.015439 | -267.339600 |
| 2277582 | 97148 | 0 | 6 | 0 | etc entendre durée | 1.975611 | 4.024389 | 2.863184 | -2.006088 | 25677.538451 | 71470.461549 | 446.015439 | -267.339600 |
| 2895549 | 97148 | 0 | 6 | 0 | heure air etc | 1.975611 | 4.024389 | 2.863184 | -2.006088 | 25677.538451 | 71470.461549 | 446.015439 | -267.339600 |
| 4588973 | 97148 | 0 | 6 | 0 | plastique heure air | 1.975611 | 4.024389 | 2.863184 | -2.006088 | 25677.538451 | 71470.461549 | 446.015439 | -267.339600 |
| 5147966 | 94907 | 0 | 3 | 0 | reportage soin intensif | 0.987805 | 2.012195 | 2.024577 | -1.418518 | 25085.211655 | 69821.788345 | 440.841106 | -264.238128 |
| 535696 | 100097 | 3673 | 135 | 33 | annoncer nouveau mesure | 55.317100 | 112.682900 | 10.713600 | -7.506476 | 27427.823168 | 76342.176832 | 438.787827 | -263.007402 |
| 3997060 | 92991 | 0 | 2 | 1 | médecin aide soignants | 0.987805 | 2.012195 | 1.018423 | -0.713558 | 24578.786780 | 68412.213220 | 436.368527 | -261.557285 |
| 4998037 | 92964 | 0 | 1 | 0 | quotidien service soin | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 384144 | 92964 | 0 | 1 | 0 | aide soignants raconter | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 1099918 | 92964 | 0 | 1 | 0 | cas grave reportage | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 5641967 | 92964 | 0 | 1 | 0 | soignants raconter réalité | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 2476802 | 92964 | 0 | 1 | 0 | filmer quotidien service | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 5308583 | 92964 | 0 | 1 | 0 | réalité chevet cas | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 2722747 | 92964 | 0 | 1 | 0 | genève médecin aide | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 2796180 | 92964 | 0 | 1 | 0 | grave reportage soin | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 1208937 | 92964 | 0 | 1 | 0 | chevet cas grave | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 5007521 | 92964 | 0 | 1 | 0 | raconter réalité chevet | 0.329268 | 0.670732 | 1.168890 | -0.818982 | 24571.650313 | 68392.349687 | 436.305172 | -261.519310 |
| 6208827 | 93394 | 595 | 2 | 1 | universitaire genève médecin | 0.987805 | 2.012195 | 1.018423 | -0.713558 | 24842.571762 | 69146.428238 | 434.928865 | -260.694358 |
| 3003996 | 90388 | 0 | 2 | 0 | il bon raison | 0.658537 | 1.341463 | 1.653060 | -1.158215 | 23890.778457 | 66497.221543 | 430.217774 | -257.870552 |
| 1196496 | 89375 | 0 | 9 | 0 | checkup check up | 2.963416 | 6.036584 | 3.506670 | -2.456946 | 23623.028772 | 65751.971228 | 427.800205 | -256.421472 |
| 6494471 | 88044 | 0 | 8 | 0 | vrai faux checkup | 2.634148 | 5.365852 | 3.306120 | -2.316431 | 23271.227358 | 64772.772642 | 424.602790 | -254.504956 |
| 1557611 | 87530 | 0 | 4 | 0 | coronavirus démêle vrai | 1.317074 | 2.682926 | 2.337780 | -1.637964 | 23135.370164 | 64394.629836 | 423.361562 | -253.760970 |
fig = px.bar(graph_interactions_media3, x="res_inter_media", y="trigramme", labels={"res_inter_media":"Résiduel de Pearson (<b>en fonction des interactions</b>)","trigramme":"Trigramme (dans les posts Facebook <b>médias</b>)"}, orientation="h", title="Trigrammes les plus caractéristiques des posts Facebook <b>médias</b> {} en 2020<br>(en fonction des interactions suscitées)".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="green", opacity=0.75, textfont_size=12)
fig
graph_interactions_nonmedia3 = khi2_3.sort_values(by=["res_inter_nonmedia"],ascending=False).head(50)
graph_interactions_nonmedia3
| interactions_media | interactions_nonmedia | obs_media | obs_nonmedia | trigramme | exp_media | exp_nonmedia | res_media | res_nonmedia | exp_inter_media | exp_inter_nonmedia | res_inter_media | res_inter_nonmedia | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5724912 | 0 | 585745 | 0 | 471 | souviens série tv | 155.085440 | 315.914560 | -12.453330 | 8.725417 | 154820.374689 | 430924.625311 | -393.472203 | 235.845426 |
| 5917743 | 0 | 534001 | 0 | 425 | série tv alffr | 139.939091 | 285.060909 | -11.829585 | 8.288391 | 141143.731324 | 392857.268676 | -375.691005 | 225.187458 |
| 1299974 | 0 | 442567 | 0 | 403 | clique image regarde | 132.695185 | 270.304815 | -11.519340 | 8.071017 | 116976.480832 | 325590.519168 | -342.018246 | 205.004161 |
| 2847983 | 0 | 343301 | 0 | 285 | générique détail série | 93.841508 | 191.158492 | -9.687183 | 6.787318 | 90739.126157 | 252561.873843 | -301.229358 | 180.555490 |
| 2078128 | 0 | 313794 | 0 | 243 | détail série mythique | 80.012233 | 162.987767 | -8.944956 | 6.267277 | 82940.024507 | 230853.975493 | -287.993098 | 172.621736 |
| 5888558 | 0 | 304065 | 0 | 190 | switzerland suisseromande romandie | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 5838415 | 0 | 304065 | 0 | 190 | suisse switzerland suisseromande | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 3910267 | 0 | 304065 | 0 | 190 | montagne lacleman leman | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 5883983 | 0 | 304065 | 0 | 190 | swiss montagne lacleman | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 3987645 | 0 | 304065 | 0 | 190 | mylausanne iglausann igerslausanne | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 3000575 | 0 | 304065 | 0 | 190 | igerslausanne vaud cantondevaud | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 3418727 | 0 | 304065 | 0 | 190 | lausanneparcoeur lausanne mylausanne | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 3000685 | 0 | 304065 | 0 | 190 | iglausann igerslausanne vaud | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 5843521 | 0 | 304065 | 0 | 190 | suisseromande romandie switzerlandpicture | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 3414017 | 0 | 304065 | 0 | 190 | lausanne mylausanne iglausann | 62.561005 | 127.438995 | -7.909552 | 5.541822 | 80368.517409 | 223696.482591 | -283.493417 | 169.924648 |
| 1074708 | 0 | 301932 | 0 | 189 | cantondevaud suisse switzerland | 62.231737 | 126.768263 | -7.888709 | 5.527219 | 79804.736482 | 222127.263518 | -282.497321 | 169.327593 |
| 6275741 | 0 | 301932 | 0 | 189 | vaud cantondevaud suisse | 62.231737 | 126.768263 | -7.888709 | 5.527219 | 79804.736482 | 222127.263518 | -282.497321 | 169.327593 |
| 6163916 | 0 | 292369 | 0 | 216 | tv alffr découvrir | 71.121985 | 144.878015 | -8.433385 | 5.908845 | 77277.105442 | 215091.894558 | -277.987599 | 166.624486 |
| 416773 | 0 | 287023 | 0 | 216 | alffr découvrir série | 71.121985 | 144.878015 | -8.433385 | 5.908845 | 75864.084891 | 211158.915109 | -275.434357 | 165.094085 |
| 1998481 | 0 | 285940 | 0 | 1635 | découvrir avenir amoureux | 538.353915 | 1096.646085 | -23.202455 | 16.256784 | 75577.833252 | 210362.166748 | -274.914229 | 164.782322 |
| 467945 | 0 | 285940 | 0 | 1635 | amoureux 3 cliquer | 538.353915 | 1096.646085 | -23.202455 | 16.256784 | 75577.833252 | 210362.166748 | -274.914229 | 164.782322 |
| 755816 | 0 | 285940 | 0 | 1635 | avenir amoureux 3 | 538.353915 | 1096.646085 | -23.202455 | 16.256784 | 75577.833252 | 210362.166748 | -274.914229 | 164.782322 |
| 5258487 | 0 | 285180 | 0 | 152 | romandie switzerlandpicture svizzera | 50.048804 | 101.951196 | -7.074518 | 4.956756 | 75376.954910 | 209803.045090 | -274.548639 | 164.563189 |
| 5888884 | 0 | 285180 | 0 | 152 | switzerlandpicture svizzera schweiz | 50.048804 | 101.951196 | -7.074518 | 4.956756 | 75376.954910 | 209803.045090 | -274.548639 | 164.563189 |
| 3989454 | 0 | 285180 | 0 | 152 | myswitzerland swiss montagne | 50.048804 | 101.951196 | -7.074518 | 4.956756 | 75376.954910 | 209803.045090 | -274.548639 | 164.563189 |
| 5881176 | 0 | 285180 | 0 | 152 | svizzera schweiz myswitzerland | 50.048804 | 101.951196 | -7.074518 | 4.956756 | 75376.954910 | 209803.045090 | -274.548639 | 164.563189 |
| 5480343 | 0 | 285180 | 0 | 152 | schweiz myswitzerland swiss | 50.048804 | 101.951196 | -7.074518 | 4.956756 | 75376.954910 | 209803.045090 | -274.548639 | 164.563189 |
| 3771940 | 0 | 277847 | 0 | 1 | meryl streep immense | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 4202867 | 0 | 277847 | 0 | 1 | oeil trouve souvenir | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 1135556 | 0 | 277847 | 0 | 1 | cerne oeil trouve | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 5194859 | 0 | 277847 | 0 | 1 | retire ride front | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 2131073 | 0 | 277847 | 0 | 1 | embrassé cerne oeil | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 6127252 | 0 | 277847 | 0 | 1 | travers étonnement face | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 5224052 | 0 | 277847 | 0 | 1 | ri embrassé cerne | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 3922388 | 0 | 277847 | 0 | 1 | montrer ri embrassé | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 844156 | 0 | 277847 | 0 | 1 | bel meryl streep | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 4598799 | 0 | 277847 | 0 | 1 | pleurer bel meryl | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 5723752 | 0 | 277847 | 0 | 1 | souvenir pleurer bel | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 6145431 | 0 | 277847 | 0 | 1 | trouve souvenir pleurer | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 4185688 | 0 | 277847 | 0 | 1 | obtenir travers étonnement | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 5227715 | 0 | 277847 | 0 | 1 | ride front obtenir | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 6705539 | 0 | 277847 | 0 | 1 | étonnement face beauté | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 6356635 | 0 | 277847 | 0 | 1 | vie bouche montrer | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 2626034 | 0 | 277847 | 0 | 1 | front obtenir travers | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 5781437 | 0 | 277847 | 0 | 1 | streep immense acteur | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 838174 | 0 | 277847 | 0 | 1 | beauté vie bouche | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 949356 | 0 | 277847 | 0 | 1 | bouche montrer ri | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 2351510 | 0 | 277847 | 0 | 1 | face beauté vie | 0.329268 | 0.670732 | -0.573819 | 0.402046 | 73438.743218 | 204408.256782 | -270.995836 | 162.433656 |
| 3017331 | 0 | 266556 | 0 | 193 | image regarde générique | 63.548811 | 129.451189 | -7.971751 | 5.585402 | 70454.378263 | 196101.621737 | -265.432436 | 159.098980 |
| 2008582 | 0 | 266044 | 0 | 213 | découvrir série tv | 70.134180 | 142.865820 | -8.374615 | 5.867668 | 70319.049695 | 195724.950305 | -265.177393 | 158.946108 |
fig = px.bar(graph_interactions_nonmedia3, x="res_inter_nonmedia", y="trigramme", labels={"res_inter_nonmedia":"Résiduel de Pearson (<b>en fonction des interactions</b>)","trigramme":"Trigramme (dans les posts Facebook <b>non-médias</b>)"}, orientation="h", title="Trigrammes les plus caractéristiques des posts Facebook <b>non-médias</b> {} en 2020<br>(en fonction des interactions suscitées)".format(pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=1000)
fig.update_traces(marker_color="lightgreen", opacity=0.75, textfont_size=12)
fig
pays = "Romandy (French Switzerland)"
termeMaj = "Lemma"
termeMin = "lemma"
yy = "mot"
media = "media"
source = graph_interactions_media1[:10]
xx= "res_inter_media"
fig = px.bar(source, x=xx, y=yy, labels={xx:"χ<sup>2</sup> residual (<b>weighed by interactions</b>)",yy:"{} (in <b>{}</b> Facebook posts)".format(termeMaj,media)}, orientation="h", title="Most characteristic {}s among <b>{}</b> Facebook posts in {} (2020)".format(termeMin,media,pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=400)
fig.update_traces(marker_color="blue", opacity=0.75, textfont_size=12)
fig
termeMaj = "Lemma"
termeMin = "lemma"
yy = "mot"
media = "non-media"
source = graph_interactions_nonmedia1[:10]
xx= "res_inter_nonmedia"
fig = px.bar(source, x=xx, y=yy, labels={xx:"χ<sup>2</sup> residual (<b>weighed by interactions</b>)",yy:"{} (in <b>{}</b> Facebook posts)".format(termeMaj,media)}, orientation="h", title="Most characteristic {}s among <b>{}</b> Facebook posts in {} (2020)".format(termeMin,media,pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=400)
fig.update_traces(marker_color="blue", opacity=0.75, textfont_size=12)
fig
termeMaj = "Bigram"
termeMin = "bigram"
yy = "bigramme"
media = "media"
source = graph_interactions_media2[:10]
xx= "res_inter_media"
fig = px.bar(source, x=xx, y=yy, labels={xx:"χ<sup>2</sup> residual (<b>weighed by interactions</b>)",yy:"{} (in <b>{}</b> Facebook posts)".format(termeMaj,media)}, orientation="h", title="Most characteristic {}s among <b>{}</b> Facebook posts in {} (2020)".format(termeMin,media,pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=400)
fig.update_traces(marker_color="blue", opacity=0.75, textfont_size=12)
fig
termeMaj = "Bigram"
termeMin = "bigram"
yy = "bigramme"
media = "non-media"
source = graph_interactions_nonmedia2[:10]
xx= "res_inter_nonmedia"
fig = px.bar(source, x=xx, y=yy, labels={xx:"χ<sup>2</sup> residual (<b>weighed by interactions</b>)",yy:"{} (in <b>{}</b> Facebook posts)".format(termeMaj,media)}, orientation="h", title="Most characteristic {}s among <b>{}</b> Facebook posts in {} (2020)".format(termeMin,media,pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=400)
fig.update_traces(marker_color="blue", opacity=0.75, textfont_size=12)
fig
termeMaj = "Trigram"
termeMin = "trigram"
yy = "trigramme"
media = "media"
source = graph_interactions_media3[:10]
xx= "res_inter_media"
fig = px.bar(source, x=xx, y=yy, labels={xx:"χ<sup>2</sup> residual (<b>weighed by interactions</b>)",yy:"{} (in <b>{}</b> Facebook posts)".format(termeMaj,media)}, orientation="h", title="Most characteristic {}s among <b>{}</b> Facebook posts in {} (2020)".format(termeMin,media,pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=400)
fig.update_traces(marker_color="blue", opacity=0.75, textfont_size=12)
fig
termeMaj = "Trigram"
termeMin = "trigram"
yy = "trigramme"
media = "non-media"
source = graph_interactions_nonmedia3[:10]
xx = "res_inter_nonmedia"
fig = px.bar(source, x=xx, y=yy, labels={xx:"χ<sup>2</sup> residual (<b>weighed by interactions</b>)",yy:"{} (in <b>{}</b> Facebook posts)".format(termeMaj,media)}, orientation="h", title="Most characteristic {}s among <b>{}</b> Facebook posts in {} (2020)".format(termeMin,media,pays))
fig.update_layout(yaxis=dict(autorange="reversed"), width=1000, height=400)
fig.update_traces(marker_color="blue", opacity=0.75, textfont_size=12)
fig